xkrs_manan/RODY
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

第一次调试

Browse Source
This commit is contained in:
552068321@qq.com 2022-11-07 14:34:35 +08:00
parent 6f7de660aa
commit 41ba5d9f44
23 changed files with 2023 additions and 152 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
SetParams.zip
View File

Binary file not shown.

225
app/controller/AlgorithmController.py
View File

@ -22,10 +22,10 @@ import sys
from pathlib import Path from pathlib import Path
# from pynvml import * # from pynvml import *
FILE = Path(__file__).resolve() # FILE = Path(__file__).resolve()
ROOT = FILE.parents[0] # YOLOv5 root directory # ROOT = FILE.parents[0] # YOLOv5 root directory
if str(ROOT) not in sys.path: # if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH # sys.path.append(str(ROOT)) # add ROOT to PATH
# sys.path.append("/mnt/sdc/algorithm/AICheck-MaskRCNN/app/maskrcnn_ppx") # sys.path.append("/mnt/sdc/algorithm/AICheck-MaskRCNN/app/maskrcnn_ppx")
# import ppx as pdx # import ppx as pdx
@ -251,7 +251,7 @@ def train_R0DY(params_str, id):
data_list = file_tool.get_file(ori_path=params.get('DatasetDir').value, type_list=params.get('classname').value) data_list = file_tool.get_file(ori_path=params.get('DatasetDir').value, type_list=params.get('classname').value)
weights = params.get('resumeModPath').value # 初始化模型绝对路径 weights = params.get('resumeModPath').value # 初始化模型绝对路径
img_size = params.get('img_size').value img_size = params.get('img_size').value
savemodel = os.path.splitext(params.get('saveModDir').value)[0] + '_' + img_size + '.pt' # 模型命名加上图像参数 savemodel = os.path.splitext(params.get('saveModDir').value)[0] + '_' + str(img_size) + '.pt' # 模型命名加上图像参数
epoches = params.get('epochnum').value epoches = params.get('epochnum').value
batch_size = params.get('batch_size').value batch_size = params.get('batch_size').value
device = params.get('device').value device = params.get('device').value
@ -261,54 +261,54 @@ def train_R0DY(params_str, id):
# 启动验证程序 # 启动验证程序
@start_test_algorithm() # @start_test_algorithm()
def validate_RODY(params_str, id): # def validate_RODY(params_str, id):
from app.yolov5.validate_server import validate_start # from app.yolov5.validate_server import validate_start
params = TrainParams() # params = TrainParams()
params.read_from_str(params_str) # params.read_from_str(params_str)
weights = params.get('modPath').value # 验证模型绝对路径 # weights = params.get('modPath').value # 验证模型绝对路径
(filename, extension) = os.path.splitext(weights) # 文件名与后缀名分开 # (filename, extension) = os.path.splitext(weights) # 文件名与后缀名分开
img_size = int(filename.split('ROD')[1].split('_')[2]) # 获取图像参数 # img_size = int(filename.split('ROD')[1].split('_')[2]) # 获取图像参数
# v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号 # # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
output = params.get('outputPath').value # output = params.get('outputPath').value
batch_size = params.get('batch_size').default # batch_size = params.get('batch_size').default
device = params.get('device').value # device = params.get('device').value
#
validate_start(weights, img_size, batch_size, device, output, id) # validate_start(weights, img_size, batch_size, device, output, id)
#
#
@start_detect_algorithm() # @start_detect_algorithm()
def detect_RODY(params_str, id): # def detect_RODY(params_str, id):
from app.yolov5.detect_server import detect_start # from app.yolov5.detect_server import detect_start
params = TrainParams() # params = TrainParams()
params.read_from_str(params_str) # params.read_from_str(params_str)
weights = params.get('modPath').value # 检测模型绝对路径 # weights = params.get('modPath').value # 检测模型绝对路径
input = params.get('inputPath').value # input = params.get('inputPath').value
outpath = params.get('outputPath').value # outpath = params.get('outputPath').value
# (filename, extension) = os.path.splitext(weights) # 文件名与后缀名分开 # # (filename, extension) = os.path.splitext(weights) # 文件名与后缀名分开
# img_size = int(filename.split('ROD')[1].split('_')[2]) #获取图像参数 # # img_size = int(filename.split('ROD')[1].split('_')[2]) #获取图像参数
# v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号 # # v_num = int(filename.split('ROD')[1].split('_')[1]) #获取版本号
# batch_size = params.get('batch_size').default # # batch_size = params.get('batch_size').default
device = params.get('device').value # device = params.get('device').value
#
detect_start(input, weights, outpath, device, id) # detect_start(input, weights, outpath, device, id)
#
#
@start_download_pt() # @start_download_pt()
def Export_model_RODY(params_str): # def Export_model_RODY(params_str):
from app.yolov5.export import Start_Model_Export # from app.yolov5.export import Start_Model_Export
import zipfile # import zipfile
params = TrainParams() # params = TrainParams()
params.read_from_str(params_str) # params.read_from_str(params_str)
exp_inputPath = params.get('exp_inputPath').value # 模型路径 # exp_inputPath = params.get('exp_inputPath').value # 模型路径
exp_device = params.get('device').value # exp_device = params.get('device').value
modellist = Start_Model_Export(exp_inputPath, exp_device) # modellist = Start_Model_Export(exp_inputPath, exp_device)
exp_outputPath = exp_inputPath.replace('pt', 'zip') # 压缩文件 # exp_outputPath = exp_inputPath.replace('pt', 'zip') # 压缩文件
zipf = zipfile.ZipFile(exp_outputPath, 'w') # zipf = zipfile.ZipFile(exp_outputPath, 'w')
for file in modellist: # for file in modellist:
zipf.write(file, arcname=Path(file).name) # 将torchscript和onnx模型压缩 # zipf.write(file, arcname=Path(file).name) # 将torchscript和onnx模型压缩
#
return exp_outputPath # return exp_outputPath
# zipf.write(modellist[1], arcname=modellist[1]) # zipf.write(modellist[1], arcname=modellist[1])
# zip_inputpath = os.path.join(exp_outputPath, "inference_model") # zip_inputpath = os.path.join(exp_outputPath, "inference_model")
# zip_outputPath = os.path.join(exp_outputPath, "inference_model.zip") # zip_outputPath = os.path.join(exp_outputPath, "inference_model.zip")
@ -347,66 +347,67 @@ def returnTrainParams():
return params_str return params_str
@obtain_test_param() # @obtain_test_param()
def returnValidateParams(): # def returnValidateParams():
# nvmlInit() # # nvmlInit()
# gpuDeviceCount = nvmlDeviceGetCount() # 获取Nvidia GPU块数 # # gpuDeviceCount = nvmlDeviceGetCount() # 获取Nvidia GPU块数
# _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)] # # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
params_list = [ # params_list = [
{"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt", # {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
"description": '验证模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False}, # "description": '验证模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
{"index": 1, "name": "batch_size", "value": 1, "description": '批次图像数量', "default": 1, "type": "I", # {"index": 1, "name": "batch_size", "value": 1, "description": '批次图像数量', "default": 1, "type": "I",
'show': False}, # 'show': False},
{"index": 2, "name": "img_size", "value": 640, "description": '训练图像大小', "default": 640, "type": "I", # {"index": 2, "name": "img_size", "value": 640, "description": '训练图像大小', "default": 640, "type": "I",
'show': False}, # 'show': False},
{"index": 3, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/', # {"index": 3, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
"description": '输出结果路径', # "description": '输出结果路径',
"default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False}, # "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
{"index": 4, "name": "device", "value": "0", "description": '训练核心', "default": "cuda", "type": "S", # {"index": 4, "name": "device", "value": "0", "description": '训练核心', "default": "cuda", "type": "S",
"items": '', 'show': False} # _kernel # "items": '', 'show': False} # _kernel
] # ]
# {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}] # # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
params_str = json.dumps(params_list) # params_str = json.dumps(params_list)
return params_str # return params_str
#
#
@obtain_detect_param() # @obtain_detect_param()
def returnDetectParams(): # def returnDetectParams():
# nvmlInit() # # nvmlInit()
# gpuDeviceCount = nvmlDeviceGetCount() # 获取Nvidia GPU块数 # # gpuDeviceCount = nvmlDeviceGetCount() # 获取Nvidia GPU块数
# _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)] # # _kernel = [f"cuda:{a}" for a in range(gpuDeviceCount)]
params_list = [ # params_list = [
{"index": 0, "name": "inputPath", "value": 'E:/aicheck/data_set/11442136178662604800/input/', # {"index": 0, "name": "inputPath", "value": 'E:/aicheck/data_set/11442136178662604800/input/',
"description": '输入图像路径', "default": './app/maskrcnn/datasets/M006B_waibi/JPEGImages', "type": "S", # "description": '输入图像路径', "default": './app/maskrcnn/datasets/M006B_waibi/JPEGImages', "type": "S",
'show': False}, # 'show': False},
{"index": 1, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/', # {"index": 1, "name": "outputPath", "value": 'E:/aicheck/data_set/11442136178662604800/val_results/',
"description": '输出结果路径', # "description": '输出结果路径',
"default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False}, # "default": './app/maskrcnn/datasets/M006B_waibi/res', "type": "S", 'show': False},
{"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt", # {"index": 0, "name": "modPath", "value": "E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt",
"description": '模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False}, # "description": '模型路径', "default": "./app/maskrcnn/saved_model/test.pt", "type": "S", 'show': False},
{"index": 3, "name": "device", "value": "0", "description": '推理核', "default": "cpu", "type": "S", # {"index": 3, "name": "device", "value": "0", "description": '推理核', "default": "cpu", "type": "S",
'show': False}, # 'show': False},
] # ]
# {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}] # # {"index": 9, "name": "saveEpoch", "value": 2, "description": '保存模型轮次', "default": 2, "type": "I", 'show': True}]
params_str = json.dumps(params_list) # params_str = json.dumps(params_list)
return params_str # return params_str
#
#
@obtain_download_pt_param() # @obtain_download_pt_param()
def returnDownloadParams(): # def returnDownloadParams():
params_list = [ # params_list = [
{"index": 0, "name": "exp_inputPath", "value": 'E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt', # {"index": 0, "name": "exp_inputPath", "value": 'E:/alg_demo-master/alg_demo/app/yolov5/圆孔_123_RODY_1_640.pt',
"description": '转化模型输入路径', # "description": '转化模型输入路径',
"default": '/mnt/sdc/IntelligentizeAI/IntelligentizeAI/data_set/weights/new磁环检测test_183504733393264640_R-DDM_11.pt/', # "default": '/mnt/sdc/IntelligentizeAI/IntelligentizeAI/data_set/weights/new磁环检测test_183504733393264640_R-DDM_11.pt/',
"type": "S", 'show': False}, # "type": "S", 'show': False},
{"index": 1, "name": "device", "value": 'gpu', "description": 'CPU或GPU', "default": 'gpu', "type": "S", # {"index": 1, "name": "device", "value": 'gpu', "description": 'CPU或GPU', "default": 'gpu', "type": "S",
'show': False} # 'show': False}
] # ]
params_str = json.dumps(params_list) # params_str = json.dumps(params_list)
return params_str # return params_str
if __name__ == '__main__': if __name__ == '__main__':
par = returnDownloadParams() par = returnTrainParams()
print(par) print(par)
Export_model_RODY(par) id='1'
train_R0DY(par,id)

779
app/models/common.py Normal file
View File

@ -0,0 +1,779 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Common modules
"""
import json
import math
import platform
import warnings
from collections import OrderedDict, namedtuple
from copy import copy
from pathlib import Path
import cv2
import numpy as np
import pandas as pd
import requests
import torch
import torch.nn as nn
from PIL import Image
from torch.cuda import amp
from app.yolov5.utils.dataloaders import exif_transpose, letterbox
from app.yolov5.utils.general import (LOGGER, ROOT, Profile, check_requirements, check_suffix, check_version, colorstr,
increment_path, make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh,
yaml_load)
from app.yolov5.utils.plots import Annotator, colors, save_one_box
from app.yolov5.utils.torch_utils import copy_attr, smart_inference_mode
def autopad(k, p=None): # kernel, padding
# Pad to 'same'
if p is None:
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
return p
class Conv(nn.Module):
# Standard convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
def forward(self, x):
return self.act(self.bn(self.conv(x)))
def forward_fuse(self, x):
return self.act(self.conv(x))
class DWConv(Conv):
# Depth-wise convolution class
def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
class DWConvTranspose2d(nn.ConvTranspose2d):
# Depth-wise transpose convolution class
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0): # ch_in, ch_out, kernel, stride, padding, padding_out
super().__init__(c1, c2, k, s, p1, p2, groups=math.gcd(c1, c2))
class TransformerLayer(nn.Module):
# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
def __init__(self, c, num_heads):
super().__init__()
self.q = nn.Linear(c, c, bias=False)
self.k = nn.Linear(c, c, bias=False)
self.v = nn.Linear(c, c, bias=False)
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
self.fc1 = nn.Linear(c, c, bias=False)
self.fc2 = nn.Linear(c, c, bias=False)
def forward(self, x):
x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
x = self.fc2(self.fc1(x)) + x
return x
class TransformerBlock(nn.Module):
# Vision Transformer https://arxiv.org/abs/2010.11929
def __init__(self, c1, c2, num_heads, num_layers):
super().__init__()
self.conv = None
if c1 != c2:
self.conv = Conv(c1, c2)
self.linear = nn.Linear(c2, c2) # learnable position embedding
self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
self.c2 = c2
def forward(self, x):
if self.conv is not None:
x = self.conv(x)
b, _, w, h = x.shape
p = x.flatten(2).permute(2, 0, 1)
return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
class Bottleneck(nn.Module):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_, c2, 3, 1, g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class BottleneckCSP(nn.Module):
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
self.cv4 = Conv(2 * c_, c2, 1, 1)
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
self.act = nn.SiLU()
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
y1 = self.cv3(self.m(self.cv1(x)))
y2 = self.cv2(x)
return self.cv4(self.act(self.bn(torch.cat((y1, y2), 1))))
class CrossConv(nn.Module):
# Cross Convolution Downsample
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, (1, k), (1, s))
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
self.add = shortcut and c1 == c2
def forward(self, x):
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
class C3(nn.Module):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c1, c_, 1, 1)
self.cv3 = Conv(2 * c_, c2, 1) # optional act=FReLU(c2)
self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
def forward(self, x):
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
class C3x(C3):
# C3 module with cross-convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e)
self.m = nn.Sequential(*(CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)))
class C3TR(C3):
# C3 module with TransformerBlock()
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e)
self.m = TransformerBlock(c_, c_, 4, n)
class C3SPP(C3):
# C3 module with SPP()
def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e)
self.m = SPP(c_, c_, k)
class C3Ghost(C3):
# C3 module with GhostBottleneck()
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
super().__init__(c1, c2, n, shortcut, g, e)
c_ = int(c2 * e) # hidden channels
self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
class SPP(nn.Module):
# Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
def __init__(self, c1, c2, k=(5, 9, 13)):
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
class SPPF(nn.Module):
# Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = Conv(c1, c_, 1, 1)
self.cv2 = Conv(c_ * 4, c2, 1, 1)
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
def forward(self, x):
x = self.cv1(x)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(torch.cat((x, y1, y2, self.m(y2)), 1))
class Focus(nn.Module):
# Focus wh information into c-space
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
# self.contract = Contract(gain=2)
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
return self.conv(torch.cat((x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]), 1))
# return self.conv(self.contract(x))
class GhostConv(nn.Module):
# Ghost Convolution https://github.com/huawei-noah/ghostnet
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
super().__init__()
c_ = c2 // 2 # hidden channels
self.cv1 = Conv(c1, c_, k, s, None, g, act)
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
def forward(self, x):
y = self.cv1(x)
return torch.cat((y, self.cv2(y)), 1)
class GhostBottleneck(nn.Module):
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
super().__init__()
c_ = c2 // 2
self.conv = nn.Sequential(
GhostConv(c1, c_, 1, 1), # pw
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False), Conv(c1, c2, 1, 1,
act=False)) if s == 2 else nn.Identity()
def forward(self, x):
return self.conv(x) + self.shortcut(x)
class Contract(nn.Module):
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
def __init__(self, gain=2):
super().__init__()
self.gain = gain
def forward(self, x):
b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
s = self.gain
x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2)
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40)
class Expand(nn.Module):
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
def __init__(self, gain=2):
super().__init__()
self.gain = gain
def forward(self, x):
b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
s = self.gain
x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80)
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160)
class Concat(nn.Module):
# Concatenate a list of tensors along dimension
def __init__(self, dimension=1):
super().__init__()
self.d = dimension
def forward(self, x):
return torch.cat(x, self.d)
class DetectMultiBackend(nn.Module):
# YOLOv5 MultiBackend class for python inference on various backends
def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False, data=None, fp16=False, fuse=True):
# Usage:
# PyTorch: weights = *.pt
# TorchScript: *.torchscript
# ONNX Runtime: *.onnx
# ONNX OpenCV DNN: *.onnx with --dnn
# OpenVINO: *.xml
# CoreML: *.mlmodel
# TensorRT: *.engine
# TensorFlow SavedModel: *_saved_model
# TensorFlow GraphDef: *.pb
# TensorFlow Lite: *.tflite
# TensorFlow Edge TPU: *_edgetpu.tflite
from models.experimental import attempt_download, attempt_load # scoped to avoid circular import
super().__init__()
w = str(weights[0] if isinstance(weights, list) else weights)
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self._model_type(w) # get backend
w = attempt_download(w) # download if not local
fp16 &= pt or jit or onnx or engine # FP16
stride = 32 # default stride
if pt: # PyTorch
model = attempt_load(weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse)
stride = max(int(model.stride.max()), 32) # model stride
names = model.module.names if hasattr(model, 'module') else model.names # get class names
model.half() if fp16 else model.float()
self.model = model # explicitly assign for to(), cpu(), cuda(), half()
elif jit: # TorchScript
LOGGER.info(f'Loading {w} for TorchScript inference...')
extra_files = {'config.txt': ''} # model metadata
model = torch.jit.load(w, _extra_files=extra_files)
model.half() if fp16 else model.float()
if extra_files['config.txt']: # load metadata dict
d = json.loads(extra_files['config.txt'],
object_hook=lambda d: {int(k) if k.isdigit() else k: v
for k, v in d.items()})
stride, names = int(d['stride']), d['names']
elif dnn: # ONNX OpenCV DNN
LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
check_requirements(('opencv-python>=4.5.4',))
net = cv2.dnn.readNetFromONNX(w)
elif onnx: # ONNX Runtime
LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
cuda = torch.cuda.is_available() and device.type != 'cpu'
check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
import onnxruntime
providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
session = onnxruntime.InferenceSession(w, providers=providers)
output_names = [x.name for x in session.get_outputs()]
meta = session.get_modelmeta().custom_metadata_map # metadata
if 'stride' in meta:
stride, names = int(meta['stride']), eval(meta['names'])
elif xml: # OpenVINO
LOGGER.info(f'Loading {w} for OpenVINO inference...')
check_requirements(('openvino',)) # requires openvino-dev: https://pypi.org/project/openvino-dev/
from openvino.runtime import Core, Layout, get_batch
ie = Core()
if not Path(w).is_file(): # if not *.xml
w = next(Path(w).glob('*.xml')) # get *.xml file from *_openvino_model dir
network = ie.read_model(model=w, weights=Path(w).with_suffix('.bin'))
if network.get_parameters()[0].get_layout().empty:
network.get_parameters()[0].set_layout(Layout("NCHW"))
batch_dim = get_batch(network)
if batch_dim.is_static:
batch_size = batch_dim.get_length()
executable_network = ie.compile_model(network, device_name="CPU") # device_name="MYRIAD" for Intel NCS2
output_layer = next(iter(executable_network.outputs))
stride, names = self._load_metadata(Path(w).with_suffix('.yaml')) # load metadata
elif engine: # TensorRT
LOGGER.info(f'Loading {w} for TensorRT inference...')
import tensorrt as trt # https://developer.nvidia.com/nvidia-tensorrt-download
check_version(trt.__version__, '7.0.0', hard=True) # require tensorrt>=7.0.0
if device.type == 'cpu':
device = torch.device('cuda:0')
Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
logger = trt.Logger(trt.Logger.INFO)
with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
model = runtime.deserialize_cuda_engine(f.read())
context = model.create_execution_context()
bindings = OrderedDict()
fp16 = False # default updated below
dynamic = False
for index in range(model.num_bindings):
name = model.get_binding_name(index)
dtype = trt.nptype(model.get_binding_dtype(index))
if model.binding_is_input(index):
if -1 in tuple(model.get_binding_shape(index)): # dynamic
dynamic = True
context.set_binding_shape(index, tuple(model.get_profile_shape(0, index)[2]))
if dtype == np.float16:
fp16 = True
shape = tuple(context.get_binding_shape(index))
im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
batch_size = bindings['images'].shape[0] # if dynamic, this is instead max batch size
elif coreml: # CoreML
LOGGER.info(f'Loading {w} for CoreML inference...')
import coremltools as ct
model = ct.models.MLModel(w)
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
if saved_model: # SavedModel
LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
import tensorflow as tf
keras = False # assume TF1 saved_model
model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
elif pb: # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
import tensorflow as tf
def wrap_frozen_graph(gd, inputs, outputs):
x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped
ge = x.graph.as_graph_element
return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
gd = tf.Graph().as_graph_def() # graph_def
with open(w, 'rb') as f:
gd.ParseFromString(f.read())
frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs="Identity:0")
elif tflite or edgetpu: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
try: # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
from tflite_runtime.interpreter import Interpreter, load_delegate
except ImportError:
import tensorflow as tf
Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
if edgetpu: # Edge TPU https://coral.ai/software/#edgetpu-runtime
LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
delegate = {
'Linux': 'libedgetpu.so.1',
'Darwin': 'libedgetpu.1.dylib',
'Windows': 'edgetpu.dll'}[platform.system()]
interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
else: # Lite
LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
interpreter = Interpreter(model_path=w) # load TFLite model
interpreter.allocate_tensors() # allocate
input_details = interpreter.get_input_details() # inputs
output_details = interpreter.get_output_details() # outputs
elif tfjs:
raise NotImplementedError('ERROR: YOLOv5 TF.js inference is not supported')
else:
raise NotImplementedError(f'ERROR: {w} is not a supported format')
# class names
if 'names' not in locals():
names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)}
if names[0] == 'n01440764' and len(names) == 1000: # ImageNet
names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] # human-readable names
self.__dict__.update(locals()) # assign all variables to self
def forward(self, im, augment=False, visualize=False):
# YOLOv5 MultiBackend inference
b, ch, h, w = im.shape # batch, channel, height, width
if self.fp16 and im.dtype != torch.float16:
im = im.half() # to FP16
if self.pt: # PyTorch
y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
elif self.jit: # TorchScript
y = self.model(im)
elif self.dnn: # ONNX OpenCV DNN
im = im.cpu().numpy() # torch to numpy
self.net.setInput(im)
y = self.net.forward()
elif self.onnx: # ONNX Runtime
im = im.cpu().numpy() # torch to numpy
y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
elif self.xml: # OpenVINO
im = im.cpu().numpy() # FP32
y = self.executable_network([im])[self.output_layer]
elif self.engine: # TensorRT
if self.dynamic and im.shape != self.bindings['images'].shape:
i_in, i_out = (self.model.get_binding_index(x) for x in ('images', 'output'))
self.context.set_binding_shape(i_in, im.shape) # reshape if dynamic
self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
self.bindings['output'].data.resize_(tuple(self.context.get_binding_shape(i_out)))
s = self.bindings['images'].shape
assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
self.binding_addrs['images'] = int(im.data_ptr())
self.context.execute_v2(list(self.binding_addrs.values()))
y = self.bindings['output'].data
elif self.coreml: # CoreML
im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
im = Image.fromarray((im[0] * 255).astype('uint8'))
# im = im.resize((192, 320), Image.ANTIALIAS)
y = self.model.predict({'image': im}) # coordinates are xywh normalized
if 'confidence' in y:
box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels
conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
else:
k = 'var_' + str(sorted(int(k.replace('var_', '')) for k in y)[-1]) # output key
y = y[k] # output
else: # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
if self.saved_model: # SavedModel
y = (self.model(im, training=False) if self.keras else self.model(im)).numpy()
elif self.pb: # GraphDef
y = self.frozen_func(x=self.tf.constant(im)).numpy()
else: # Lite or Edge TPU
input, output = self.input_details[0], self.output_details[0]
int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model
if int8:
scale, zero_point = input['quantization']
im = (im / scale + zero_point).astype(np.uint8) # de-scale
self.interpreter.set_tensor(input['index'], im)
self.interpreter.invoke()
y = self.interpreter.get_tensor(output['index'])
if int8:
scale, zero_point = output['quantization']
y = (y.astype(np.float32) - zero_point) * scale # re-scale
y[..., :4] *= [w, h, w, h] # xywh normalized to pixels
if isinstance(y, (list, tuple)):
return self.from_numpy(y[0]) if len(y) == 1 else [self.from_numpy(x) for x in y]
else:
return self.from_numpy(y)
def from_numpy(self, x):
return torch.from_numpy(x).to(self.device) if isinstance(x, np.ndarray) else x
def warmup(self, imgsz=(1, 3, 640, 640)):
# Warmup model by running inference once
warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb
if any(warmup_types) and self.device.type != 'cpu':
im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device) # input
for _ in range(2 if self.jit else 1): #
self.forward(im) # warmup
@staticmethod
def _model_type(p='path/to/model.pt'):
# Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
from export import export_formats
suffixes = list(export_formats().Suffix) + ['.xml'] # export suffixes
check_suffix(p, suffixes) # checks
p = Path(p).name # eliminate trailing separators
pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes)
xml |= xml2 # *_openvino_model or *.xml
tflite &= not edgetpu # *.tflite
return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs
@staticmethod
def _load_metadata(f=Path('path/to/meta.yaml')):
# Load metadata from meta.yaml if it exists
if f.exists():
d = yaml_load(f)
return d['stride'], d['names'] # assign stride, names
return None, None
class AutoShape(nn.Module):
# YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
conf = 0.25 # NMS confidence threshold
iou = 0.45 # NMS IoU threshold
agnostic = False # NMS class-agnostic
multi_label = False # NMS multiple labels per box
classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
max_det = 1000 # maximum number of detections per image
amp = False # Automatic Mixed Precision (AMP) inference
def __init__(self, model, verbose=True):
super().__init__()
if verbose:
LOGGER.info('Adding AutoShape... ')
copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=()) # copy attributes
self.dmb = isinstance(model, DetectMultiBackend) # DetectMultiBackend() instance
self.pt = not self.dmb or model.pt # PyTorch model
self.model = model.eval()
if self.pt:
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect()
m.inplace = False # Detect.inplace=False for safe multithread inference
def _apply(self, fn):
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
self = super()._apply(fn)
if self.pt:
m = self.model.model.model[-1] if self.dmb else self.model.model[-1] # Detect()
m.stride = fn(m.stride)
m.grid = list(map(fn, m.grid))
if isinstance(m.anchor_grid, list):
m.anchor_grid = list(map(fn, m.anchor_grid))
return self
@smart_inference_mode()
def forward(self, ims, size=640, augment=False, profile=False):
# Inference from various sources. For size(height=640, width=1280), RGB images example inputs are:
# file: ims = 'data/images/zidane.jpg' # str or PosixPath
# URI: = 'https://ultralytics.com/images/zidane.jpg'
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
# PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
# numpy: = np.zeros((640,1280,3)) # HWC
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
dt = (Profile(), Profile(), Profile())
with dt[0]:
if isinstance(size, int): # expand
size = (size, size)
p = next(self.model.parameters()) if self.pt else torch.empty(1, device=self.model.device) # param
autocast = self.amp and (p.device.type != 'cpu') # Automatic Mixed Precision (AMP) inference
if isinstance(ims, torch.Tensor): # torch
with amp.autocast(autocast):
return self.model(ims.to(p.device).type_as(p), augment, profile) # inference
# Pre-process
n, ims = (len(ims), list(ims)) if isinstance(ims, (list, tuple)) else (1, [ims]) # number, list of images
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
for i, im in enumerate(ims):
f = f'image{i}' # filename
if isinstance(im, (str, Path)): # filename or uri
im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
im = np.asarray(exif_transpose(im))
elif isinstance(im, Image.Image): # PIL Image
im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
files.append(Path(f).with_suffix('.jpg').name)
if im.shape[0] < 5: # image in CHW
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
im = im[..., :3] if im.ndim == 3 else cv2.cvtColor(im, cv2.COLOR_GRAY2BGR) # enforce 3ch input
s = im.shape[:2] # HWC
shape0.append(s) # image shape
g = max(size) / max(s) # gain
shape1.append([y * g for y in s])
ims[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] if self.pt else size # inf shape
x = [letterbox(im, shape1, auto=False)[0] for im in ims] # pad
x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2))) # stack and BHWC to BCHW
x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
with amp.autocast(autocast):
# Inference
with dt[1]:
y = self.model(x, augment, profile) # forward
# Post-process
with dt[2]:
y = non_max_suppression(y if self.dmb else y[0],
self.conf,
self.iou,
self.classes,
self.agnostic,
self.multi_label,
max_det=self.max_det) # NMS
for i in range(n):
scale_coords(shape1, y[i][:, :4], shape0[i])
return Detections(ims, y, files, dt, self.names, x.shape)
class Detections:
# YOLOv5 detections class for inference results
def __init__(self, ims, pred, files, times=(0, 0, 0), names=None, shape=None):
super().__init__()
d = pred[0].device # device
gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in ims] # normalizations
self.ims = ims # list of images as numpy arrays
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
self.names = names # class names
self.files = files # image filenames
self.times = times # profiling times
self.xyxy = pred # xyxy pixels
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
self.n = len(self.pred) # number of images (batch size)
self.t = tuple(x.t / self.n * 1E3 for x in times) # timestamps (ms)
self.s = shape # inference BCHW shape
def display(self, pprint=False, show=False, save=False, crop=False, render=False, labels=True, save_dir=Path('')):
crops = []
for i, (im, pred) in enumerate(zip(self.ims, self.pred)):
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
if pred.shape[0]:
for c in pred[:, -1].unique():
n = (pred[:, -1] == c).sum() # detections per class
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
if show or save or render or crop:
annotator = Annotator(im, example=str(self.names))
for *box, conf, cls in reversed(pred): # xyxy, confidence, class
label = f'{self.names[int(cls)]} {conf:.2f}'
if crop:
file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
crops.append({
'box': box,
'conf': conf,
'cls': cls,
'label': label,
'im': save_one_box(box, im, file=file, save=save)})
else: # all others
annotator.box_label(box, label if labels else '', color=colors(cls))
im = annotator.im
else:
s += '(no detections)'
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
if pprint:
print(s.rstrip(', '))
if show:
im.show(self.files[i]) # show
if save:
f = self.files[i]
im.save(save_dir / f) # save
if i == self.n - 1:
LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
if render:
self.ims[i] = np.asarray(im)
if crop:
if save:
LOGGER.info(f'Saved results to {save_dir}\n')
return crops
def print(self):
self.display(pprint=True) # print results
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % self.t)
def show(self, labels=True):
self.display(show=True, labels=labels) # show results
def save(self, labels=True, save_dir='runs/detect/exp'):
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
self.display(save=True, labels=labels, save_dir=save_dir) # save results
def crop(self, save=True, save_dir='runs/detect/exp'):
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
return self.display(crop=True, save=save, save_dir=save_dir) # crop results
def render(self, labels=True):
self.display(render=True, labels=labels) # render results
return self.ims
def pandas(self):
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
new = copy(self) # return copy
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
return new
def tolist(self):
# return a list of Detections objects, i.e. 'for result in results.tolist():'
r = range(self.n) # iterable
x = [Detections([self.ims[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
# for d in x:
# for k in ['ims', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
# setattr(d, k, getattr(d, k)[0]) # pop out of list
return x
def __len__(self):
return self.n # override len(results)
def __str__(self):
self.print() # override print(results)
return ''
class Classify(nn.Module):
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
c_ = 1280 # efficientnet_b0 size
self.conv = Conv(c1, c_, k, s, autopad(k, p), g)
self.pool = nn.AdaptiveAvgPool2d(1) # to x(b,c_,1,1)
self.drop = nn.Dropout(p=0.0, inplace=True)
self.linear = nn.Linear(c_, c2) # to x(b,c2)
def forward(self, x):
if isinstance(x, list):
x = torch.cat(x, 1)
return self.linear(self.drop(self.pool(self.conv(x)).flatten(1)))

111
app/models/experimental.py Normal file
View File

@ -0,0 +1,111 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
Experimental modules
"""
import math
import numpy as np
import torch
import torch.nn as nn
from app.yolov5.utils.downloads import attempt_download
class Sum(nn.Module):
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
def __init__(self, n, weight=False): # n: number of inputs
super().__init__()
self.weight = weight # apply weights boolean
self.iter = range(n - 1) # iter object
if weight:
self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights
def forward(self, x):
y = x[0] # no weight
if self.weight:
w = torch.sigmoid(self.w) * 2
for i in self.iter:
y = y + x[i + 1] * w[i]
else:
for i in self.iter:
y = y + x[i + 1]
return y
class MixConv2d(nn.Module):
# Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy
super().__init__()
n = len(k) # number of convolutions
if equal_ch: # equal c_ per group
i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices
c_ = [(i == g).sum() for g in range(n)] # intermediate channels
else: # equal weight.numel() per group
b = [c2] + [0] * n
a = np.eye(n + 1, n, k=-1)
a -= np.roll(a, 1, axis=1)
a *= np.array(k) ** 2
a[0] = 1
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
self.m = nn.ModuleList([
nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
self.bn = nn.BatchNorm2d(c2)
self.act = nn.SiLU()
def forward(self, x):
return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
class Ensemble(nn.ModuleList):
# Ensemble of models
def __init__(self):
super().__init__()
def forward(self, x, augment=False, profile=False, visualize=False):
y = [module(x, augment, profile, visualize)[0] for module in self]
# y = torch.stack(y).max(0)[0] # max ensemble
# y = torch.stack(y).mean(0) # mean ensemble
y = torch.cat(y, 1) # nms ensemble
return y, None # inference, train output
def attempt_load(weights, device=None, inplace=True, fuse=True):
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
from app.yolov5.models.yolo import Detect, Model
model = Ensemble()
for w in weights if isinstance(weights, list) else [weights]:
ckpt = torch.load(attempt_download(w), map_location='cpu') # load
ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float() # FP32 model
# Model compatibility updates
if not hasattr(ckpt, 'stride'):
ckpt.stride = torch.tensor([32.])
if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
ckpt.names = dict(enumerate(ckpt.names)) # convert to dict
model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval()) # model in eval mode
# Module compatibility updates
for m in model.modules():
t = type(m)
if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
m.inplace = inplace # torch 1.7.0 compatibility
if t is Detect and not isinstance(m.anchor_grid, list):
delattr(m, 'anchor_grid')
setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
m.recompute_scale_factor = None # torch 1.11.0 compatibility
# Return model
if len(model) == 1:
return model[-1]
# Return detection ensemble
print(f'Ensemble created with {weights}\n')
for k in 'names', 'nc', 'yaml':
setattr(model, k, getattr(model[0], k))
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
return model

574
app/models/tf.py Normal file
View File

@ -0,0 +1,574 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
TensorFlow, Keras and TFLite versions of YOLOv5
Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
Usage:
$ python models/tf.py --weights yolov5s.pt
Export:
$ python export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
"""
import argparse
import sys
from copy import deepcopy
from pathlib import Path
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
# ROOT = ROOT.relative_to(Path.cwd()) # relative
import numpy as np
import tensorflow as tf
import torch
import torch.nn as nn
from tensorflow import keras
from app.yolov5.models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv,
DWConvTranspose2d, Focus, autopad)
from app.yolov5.models.experimental import MixConv2d, attempt_load
from app.yolov5.models.yolo import Detect
from app.yolov5.utils.activations import SiLU
from app.yolov5.utils.general import LOGGER, make_divisible, print_args
class TFBN(keras.layers.Layer):
# TensorFlow BatchNormalization wrapper
def __init__(self, w=None):
super().__init__()
self.bn = keras.layers.BatchNormalization(
beta_initializer=keras.initializers.Constant(w.bias.numpy()),
gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
epsilon=w.eps)
def call(self, inputs):
return self.bn(inputs)
class TFPad(keras.layers.Layer):
# Pad inputs in spatial dimensions 1 and 2
def __init__(self, pad):
super().__init__()
if isinstance(pad, int):
self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
else: # tuple/list
self.pad = tf.constant([[0, 0], [pad[0], pad[0]], [pad[1], pad[1]], [0, 0]])
def call(self, inputs):
return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
class TFConv(keras.layers.Layer):
# Standard convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
# TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
# see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
conv = keras.layers.Conv2D(
filters=c2,
kernel_size=k,
strides=s,
padding='SAME' if s == 1 else 'VALID',
use_bias=not hasattr(w, 'bn'),
kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
self.act = activations(w.act) if act else tf.identity
def call(self, inputs):
return self.act(self.bn(self.conv(inputs)))
class TFDWConv(keras.layers.Layer):
# Depthwise convolution
def __init__(self, c1, c2, k=1, s=1, p=None, act=True, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert c2 % c1 == 0, f'TFDWConv() output={c2} must be a multiple of input={c1} channels'
conv = keras.layers.DepthwiseConv2D(
kernel_size=k,
depth_multiplier=c2 // c1,
strides=s,
padding='SAME' if s == 1 else 'VALID',
use_bias=not hasattr(w, 'bn'),
depthwise_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
self.act = activations(w.act) if act else tf.identity
def call(self, inputs):
return self.act(self.bn(self.conv(inputs)))
class TFDWConvTranspose2d(keras.layers.Layer):
# Depthwise ConvTranspose2d
def __init__(self, c1, c2, k=1, s=1, p1=0, p2=0, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert c1 == c2, f'TFDWConv() output={c2} must be equal to input={c1} channels'
assert k == 4 and p1 == 1, 'TFDWConv() only valid for k=4 and p1=1'
weight, bias = w.weight.permute(2, 3, 1, 0).numpy(), w.bias.numpy()
self.c1 = c1
self.conv = [
keras.layers.Conv2DTranspose(filters=1,
kernel_size=k,
strides=s,
padding='VALID',
output_padding=p2,
use_bias=True,
kernel_initializer=keras.initializers.Constant(weight[..., i:i + 1]),
bias_initializer=keras.initializers.Constant(bias[i])) for i in range(c1)]
def call(self, inputs):
return tf.concat([m(x) for m, x in zip(self.conv, tf.split(inputs, self.c1, 3))], 3)[:, 1:-1, 1:-1]
class TFFocus(keras.layers.Layer):
# Focus wh information into c-space
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
# ch_in, ch_out, kernel, stride, padding, groups
super().__init__()
self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c)
# inputs = inputs / 255 # normalize 0-255 to 0-1
inputs = [inputs[:, ::2, ::2, :], inputs[:, 1::2, ::2, :], inputs[:, ::2, 1::2, :], inputs[:, 1::2, 1::2, :]]
return self.conv(tf.concat(inputs, 3))
class TFBottleneck(keras.layers.Layer):
# Standard bottleneck
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
self.add = shortcut and c1 == c2
def call(self, inputs):
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
class TFCrossConv(keras.layers.Layer):
# Cross Convolution
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False, w=None):
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = TFConv(c1, c_, (1, k), (1, s), w=w.cv1)
self.cv2 = TFConv(c_, c2, (k, 1), (s, 1), g=g, w=w.cv2)
self.add = shortcut and c1 == c2
def call(self, inputs):
return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
class TFConv2d(keras.layers.Layer):
# Substitution for PyTorch nn.Conv2D
def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
super().__init__()
assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
self.conv = keras.layers.Conv2D(filters=c2,
kernel_size=k,
strides=s,
padding='VALID',
use_bias=bias,
kernel_initializer=keras.initializers.Constant(
w.weight.permute(2, 3, 1, 0).numpy()),
bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None)
def call(self, inputs):
return self.conv(inputs)
class TFBottleneckCSP(keras.layers.Layer):
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
# ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
self.bn = TFBN(w.bn)
self.act = lambda x: keras.activations.swish(x)
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
def call(self, inputs):
y1 = self.cv3(self.m(self.cv1(inputs)))
y2 = self.cv2(inputs)
return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
class TFC3(keras.layers.Layer):
# CSP Bottleneck with 3 convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
# ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
def call(self, inputs):
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
class TFC3x(keras.layers.Layer):
# 3 module with cross-convolutions
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
# ch_in, ch_out, number, shortcut, groups, expansion
super().__init__()
c_ = int(c2 * e) # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
self.m = keras.Sequential([
TFCrossConv(c_, c_, k=3, s=1, g=g, e=1.0, shortcut=shortcut, w=w.m[j]) for j in range(n)])
def call(self, inputs):
return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
class TFSPP(keras.layers.Layer):
# Spatial pyramid pooling layer used in YOLOv3-SPP
def __init__(self, c1, c2, k=(5, 9, 13), w=None):
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
def call(self, inputs):
x = self.cv1(inputs)
return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
class TFSPPF(keras.layers.Layer):
# Spatial pyramid pooling-Fast layer
def __init__(self, c1, c2, k=5, w=None):
super().__init__()
c_ = c1 // 2 # hidden channels
self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
def call(self, inputs):
x = self.cv1(inputs)
y1 = self.m(x)
y2 = self.m(y1)
return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
class TFDetect(keras.layers.Layer):
# TF YOLOv5 Detect layer
def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer
super().__init__()
self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
self.nc = nc # number of classes
self.no = nc + 5 # number of outputs per anchor
self.nl = len(anchors) # number of detection layers
self.na = len(anchors[0]) // 2 # number of anchors
self.grid = [tf.zeros(1)] * self.nl # init grid
self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]), [self.nl, 1, -1, 1, 2])
self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
self.training = False # set to False after building model
self.imgsz = imgsz
for i in range(self.nl):
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
self.grid[i] = self._make_grid(nx, ny)
def call(self, inputs):
z = [] # inference output
x = []
for i in range(self.nl):
x.append(self.m[i](inputs[i]))
# x(bs,20,20,255) to x(bs,3,20,20,85)
ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
x[i] = tf.reshape(x[i], [-1, ny * nx, self.na, self.no])
if not self.training: # inference
y = tf.sigmoid(x[i])
grid = tf.transpose(self.grid[i], [0, 2, 1, 3]) - 0.5
anchor_grid = tf.transpose(self.anchor_grid[i], [0, 2, 1, 3]) * 4
xy = (y[..., 0:2] * 2 + grid) * self.stride[i] # xy
wh = y[..., 2:4] ** 2 * anchor_grid
# Normalize xywh to 0-1 to reduce calibration error
xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
y = tf.concat([xy, wh, y[..., 4:]], -1)
z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
return tf.transpose(x, [0, 2, 1, 3]) if self.training else (tf.concat(z, 1), x)
@staticmethod
def _make_grid(nx=20, ny=20):
# yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
# return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
class TFUpsample(keras.layers.Layer):
# TF version of torch.nn.Upsample()
def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
super().__init__()
assert scale_factor == 2, "scale_factor must be 2"
self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
# self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
# with default arguments: align_corners=False, half_pixel_centers=False
# self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
# size=(x.shape[1] * 2, x.shape[2] * 2))
def call(self, inputs):
return self.upsample(inputs)
class TFConcat(keras.layers.Layer):
# TF version of torch.concat()
def __init__(self, dimension=1, w=None):
super().__init__()
assert dimension == 1, "convert only NCHW to NHWC concat"
self.d = 3
def call(self, inputs):
return tf.concat(inputs, self.d)
def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m_str = m
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
try:
args[j] = eval(a) if isinstance(a, str) else a # eval strings
except NameError:
pass
n = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in [
nn.Conv2d, Conv, DWConv, DWConvTranspose2d, Bottleneck, SPP, SPPF, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3x]:
c1, c2 = ch[f], args[0]
c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3x]:
args.insert(2, n)
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
elif m is Detect:
args.append([ch[x + 1] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
args.append(imgsz)
else:
c2 = ch[f]
tf_m = eval('TF' + m_str.replace('nn.', ''))
m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
else tf_m(*args, w=model.model[i]) # module
torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum(x.numel() for x in torch_m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
ch.append(c2)
return keras.Sequential(layers), sorted(save)
class TFModel:
# TF YOLOv5 model
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg) as f:
self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
# Define model
if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
def predict(self,
inputs,
tf_nms=False,
agnostic_nms=False,
topk_per_class=100,
topk_all=100,
iou_thres=0.45,
conf_thres=0.25):
y = [] # outputs
x = inputs
for m in self.model.layers:
if m.f != -1: # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
x = m(x) # run
y.append(x if m.i in self.savelist else None) # save output
# Add TensorFlow NMS
if tf_nms:
boxes = self._xywh2xyxy(x[0][..., :4])
probs = x[0][:, :, 4:5]
classes = x[0][:, :, 5:]
scores = probs * classes
if agnostic_nms:
nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
else:
boxes = tf.expand_dims(boxes, 2)
nms = tf.image.combined_non_max_suppression(boxes,
scores,
topk_per_class,
topk_all,
iou_thres,
conf_thres,
clip_boxes=False)
return nms, x[1]
return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
# x = x[0][0] # [x(1,6300,85), ...] to x(6300,85)
# xywh = x[..., :4] # x(6300,4) boxes
# conf = x[..., 4:5] # x(6300,1) confidences
# cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes
# return tf.concat([conf, cls, xywh], 1)
@staticmethod
def _xywh2xyxy(xywh):
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
class AgnosticNMS(keras.layers.Layer):
# TF Agnostic NMS
def call(self, input, topk_all, iou_thres, conf_thres):
# wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres),
input,
fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
name='agnostic_nms')
@staticmethod
def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
boxes, classes, scores = x
class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
scores_inp = tf.reduce_max(scores, -1)
selected_inds = tf.image.non_max_suppression(boxes,
scores_inp,
max_output_size=topk_all,
iou_threshold=iou_thres,
score_threshold=conf_thres)
selected_boxes = tf.gather(boxes, selected_inds)
padded_boxes = tf.pad(selected_boxes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
mode="CONSTANT",
constant_values=0.0)
selected_scores = tf.gather(scores_inp, selected_inds)
padded_scores = tf.pad(selected_scores,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode="CONSTANT",
constant_values=-1.0)
selected_classes = tf.gather(class_inds, selected_inds)
padded_classes = tf.pad(selected_classes,
paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
mode="CONSTANT",
constant_values=-1.0)
valid_detections = tf.shape(selected_inds)[0]
return padded_boxes, padded_scores, padded_classes, valid_detections
def activations(act=nn.SiLU):
# Returns TF activation from input PyTorch activation
if isinstance(act, nn.LeakyReLU):
return lambda x: keras.activations.relu(x, alpha=0.1)
elif isinstance(act, nn.Hardswish):
return lambda x: x * tf.nn.relu6(x + 3) * 0.166666667
elif isinstance(act, (nn.SiLU, SiLU)):
return lambda x: keras.activations.swish(x)
else:
raise Exception(f'no matching TensorFlow activation found for PyTorch activation {act}')
def representative_dataset_gen(dataset, ncalib=100):
# Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
im = np.transpose(img, [1, 2, 0])
im = np.expand_dims(im, axis=0).astype(np.float32)
im /= 255
yield [im]
if n >= ncalib:
break
def run(
weights=ROOT / 'yolov5s.pt', # weights path
imgsz=(640, 640), # inference size h,w
batch_size=1, # batch size
dynamic=False, # dynamic batch size
):
# PyTorch model
im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
model = attempt_load(weights, device=torch.device('cpu'), inplace=True, fuse=False)
_ = model(im) # inference
model.info()
# TensorFlow model
im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
_ = tf_model.predict(im) # inference
# Keras model
im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
keras_model.summary()
LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
def parse_opt():
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
opt = parser.parse_args()
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
print_args(vars(opt))
return opt
def main(opt):
run(**vars(opt))
if __name__ == "__main__":
opt = parse_opt()
main(opt)

357
app/models/yolo.py Normal file
View File

@ -0,0 +1,357 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
YOLO-specific modules
Usage:
$ python models/yolo.py --cfg yolov5s.yaml
"""
import argparse
import contextlib
import os
import platform
import sys
from copy import deepcopy
from pathlib import Path
FILE = Path(__file__).resolve()
ROOT = FILE.parents[1] # YOLOv5 root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
if platform.system() != 'Windows':
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from app.yolov5.models.common import *
from app.yolov5.models.experimental import *
from app.yolov5.utils.autoanchor import check_anchor_order
from app.yolov5.utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
from app.yolov5.utils.plots import feature_visualization
from app.yolov5.utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
time_sync)
try:
import thop # for FLOPs computation
except ImportError:
thop = None
class Detect(nn.Module):
stride = None # strides computed during build
dynamic = False # force grid reconstruction
export = False # export mode
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
super().__init__()
self.nc = nc # number of classes
self.no = nc + 5 # number of outputs per anchor
self.nl = len(anchors) # number of detection layers
self.na = len(anchors[0]) // 2 # number of anchors
self.grid = [torch.empty(1)] * self.nl # init grid
self.anchor_grid = [torch.empty(1)] * self.nl # init anchor grid
self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
self.inplace = inplace # use inplace ops (e.g. slice assignment)
def forward(self, x):
z = [] # inference output
for i in range(self.nl):
x[i] = self.m[i](x[i]) # conv
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
if not self.training: # inference
if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
y = x[i].sigmoid()
if self.inplace:
y[..., 0:2] = (y[..., 0:2] * 2 + self.grid[i]) * self.stride[i] # xy
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
xy, wh, conf = y.split((2, 2, self.nc + 1), 4) # y.tensor_split((2, 4, 5), 4) # torch 1.8.0
xy = (xy * 2 + self.grid[i]) * self.stride[i] # xy
wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh
y = torch.cat((xy, wh, conf), 4)
z.append(y.view(bs, -1, self.no))
return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
d = self.anchors[i].device
t = self.anchors[i].dtype
shape = 1, self.na, ny, nx, 2 # grid shape
y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x) # torch>=0.7 compatibility
grid = torch.stack((xv, yv), 2).expand(shape) - 0.5 # add grid offset, i.e. y = 2.0 * x - 0.5
anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
return grid, anchor_grid
class BaseModel(nn.Module):
# YOLOv5 base model
def forward(self, x, profile=False, visualize=False):
return self._forward_once(x, profile, visualize) # single-scale inference, train
def _forward_once(self, x, profile=False, visualize=False):
y, dt = [], [] # outputs
for m in self.model:
if m.f != -1: # if not from previous layer
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
if profile:
self._profile_one_layer(m, x, dt)
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if visualize:
feature_visualization(x, m.type, m.i, save_dir=visualize)
return x
def _profile_one_layer(self, m, x, dt):
c = m == self.model[-1] # is final layer, copy input as inplace fix
o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
t = time_sync()
for _ in range(10):
m(x.copy() if c else x)
dt.append((time_sync() - t) * 100)
if m == self.model[0]:
LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} module")
LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
if c:
LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
LOGGER.info('Fusing layers... ')
for m in self.model.modules():
if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
delattr(m, 'bn') # remove batchnorm
m.forward = m.forward_fuse # update forward
self.info()
return self
def info(self, verbose=False, img_size=640): # print model information
model_info(self, verbose, img_size)
def _apply(self, fn):
# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
self = super()._apply(fn)
m = self.model[-1] # Detect()
if isinstance(m, Detect):
m.stride = fn(m.stride)
m.grid = list(map(fn, m.grid))
if isinstance(m.anchor_grid, list):
m.anchor_grid = list(map(fn, m.anchor_grid))
return self
class DetectionModel(BaseModel):
# YOLOv5 detection model
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
super().__init__()
if isinstance(cfg, dict):
self.yaml = cfg # model dict
else: # is *.yaml
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg, encoding='ascii', errors='ignore') as f:
self.yaml = yaml.safe_load(f) # model dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
if nc and nc != self.yaml['nc']:
LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
self.yaml['nc'] = nc # override yaml value
if anchors:
LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
self.yaml['anchors'] = round(anchors) # override yaml value
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
self.inplace = self.yaml.get('inplace', True)
# Build strides, anchors
m = self.model[-1] # Detect()
if isinstance(m, Detect):
s = 256 # 2x min stride
m.inplace = self.inplace
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.empty(1, ch, s, s))]) # forward
check_anchor_order(m) # must be in pixel-space (not grid-space)
m.anchors /= m.stride.view(-1, 1, 1)
self.stride = m.stride
self._initialize_biases() # only run once
# Init weights, biases
initialize_weights(self)
self.info()
LOGGER.info('')
def forward(self, x, augment=False, profile=False, visualize=False):
if augment:
return self._forward_augment(x) # augmented inference, None
return self._forward_once(x, profile, visualize) # single-scale inference, train
def _forward_augment(self, x):
img_size = x.shape[-2:] # height, width
s = [1, 0.83, 0.67] # scales
f = [None, 3, None] # flips (2-ud, 3-lr)
y = [] # outputs
for si, fi in zip(s, f):
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
yi = self._forward_once(xi)[0] # forward
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
yi = self._descale_pred(yi, fi, si, img_size)
y.append(yi)
y = self._clip_augmented(y) # clip augmented tails
return torch.cat(y, 1), None # augmented inference, train
def _descale_pred(self, p, flips, scale, img_size):
# de-scale predictions following augmented inference (inverse operation)
if self.inplace:
p[..., :4] /= scale # de-scale
if flips == 2:
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
elif flips == 3:
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
else:
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
if flips == 2:
y = img_size[0] - y # de-flip ud
elif flips == 3:
x = img_size[1] - x # de-flip lr
p = torch.cat((x, y, wh, p[..., 4:]), -1)
return p
def _clip_augmented(self, y):
# Clip YOLOv5 augmented inference tails
nl = self.model[-1].nl # number of detection layers (P3-P5)
g = sum(4 ** x for x in range(nl)) # grid points
e = 1 # exclude layer count
i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
y[0] = y[0][:, :-i] # large
i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
y[-1] = y[-1][:, i:] # small
return y
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
# https://arxiv.org/abs/1708.02002 section 3.3
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
m = self.model[-1] # Detect() module
for mi, s in zip(m.m, m.stride): # from
b = mi.bias.view(m.na, -1).detach() # conv.bias(255) to (3,85)
b[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
b[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
Model = DetectionModel # retain YOLOv5 'Model' class for backwards compatibility
class ClassificationModel(BaseModel):
# YOLOv5 classification model
def __init__(self, cfg=None, model=None, nc=1000, cutoff=10): # yaml, model, number of classes, cutoff index
super().__init__()
self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)
def _from_detection_model(self, model, nc=1000, cutoff=10):
# Create a YOLOv5 classification model from a YOLOv5 detection model
if isinstance(model, DetectMultiBackend):
model = model.model # unwrap DetectMultiBackend
model.model = model.model[:cutoff] # backbone
m = model.model[-1] # last layer
ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels # ch into module
c = Classify(ch, nc) # Classify()
c.i, c.f, c.type = m.i, m.f, 'models.common.Classify' # index, from, type
model.model[-1] = c # replace
self.model = model.model
self.stride = model.stride
self.save = []
self.nc = nc
def _from_yaml(self, cfg):
# Create a YOLOv5 classification model from a *.yaml file
self.model = None
def parse_model(d, ch): # model_dict, input_channels(3)
LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
m = eval(m) if isinstance(m, str) else m # eval strings
for j, a in enumerate(args):
with contextlib.suppress(NameError):
args[j] = eval(a) if isinstance(a, str) else a # eval strings
n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
if m in (Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x):
c1, c2 = ch[f], args[0]
if c2 != no: # if not output
c2 = make_divisible(c2 * gw, 8)
args = [c1, c2, *args[1:]]
if m in [BottleneckCSP, C3, C3TR, C3Ghost, C3x]:
args.insert(2, n) # number of repeats
n = 1
elif m is nn.BatchNorm2d:
args = [ch[f]]
elif m is Concat:
c2 = sum(ch[x] for x in f)
elif m is Detect:
args.append([ch[x] for x in f])
if isinstance(args[1], int): # number of anchors
args[1] = [list(range(args[1] * 2))] * len(f)
elif m is Contract:
c2 = ch[f] * args[0] ** 2
elif m is Expand:
c2 = ch[f] // args[0] ** 2
else:
c2 = ch[f]
m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
t = str(m)[8:-2].replace('__main__.', '') # module type
np = sum(x.numel() for x in m_.parameters()) # number params
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
layers.append(m_)
if i == 0:
ch = []
ch.append(c2)
return nn.Sequential(*layers), sorted(save)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--profile', action='store_true', help='profile model speed')
parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
opt = parser.parse_args()
opt.cfg = check_yaml(opt.cfg) # check YAML
print_args(vars(opt))
device = select_device(opt.device)
# Create model
im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
model = Model(opt.cfg).to(device)
# Options
if opt.line_profile: # profile layer by layer
model(im, profile=True)
elif opt.profile: # profile forward-backward
results = profile(input=im, ops=[model], n=3)
elif opt.test: # test all models
for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
try:
_ = Model(cfg)
except Exception as e:
print(f'Error in {cfg}: {e}')
else: # report fused model summary
model.fuse()

48
app/models/yolov5s.yaml Normal file
View File

@ -0,0 +1,48 @@
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
# Parameters
nc: 2 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, C3, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 6, C3, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, C3, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 3, C3, [1024]],
[-1, 1, SPPF, [1024, 5]], # 9
]
# YOLOv5 v6.0 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, C3, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]

1
app/run.py
View File

@ -10,6 +10,7 @@ from flask_sockets import Sockets
import sys import sys
#sys.path.append("/mnt/sdc/algorithm/AICheck-MaskRCNN") #sys.path.append("/mnt/sdc/algorithm/AICheck-MaskRCNN")
sys.path.append('E:/alg_demo-master/alg_demo/app/yolov5')
from app.core.common_utils import logger from app.core.common_utils import logger
from app.core.err_handler import page_not_found, method_not_allowed, exception_500, exception_400 from app.core.err_handler import page_not_found, method_not_allowed, exception_500, exception_400

12
app/yolov5/classify/predict.py
View File

@ -39,13 +39,13 @@ if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend from app.yolov5.models.common import DetectMultiBackend
from utils.augmentations import classify_transforms from app.yolov5.utils.augmentations import classify_transforms
from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams from app.yolov5.utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, from app.yolov5.utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2,
increment_path, print_args, strip_optimizer) increment_path, print_args, strip_optimizer)
from utils.plots import Annotator from app.yolov5.utils.plots import Annotator
from utils.torch_utils import select_device, smart_inference_mode from app.yolov5.utils.torch_utils import select_device, smart_inference_mode
@smart_inference_mode() @smart_inference_mode()

16
app/yolov5/classify/train.py
View File

@ -36,15 +36,15 @@ if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from classify import val as validate from app.yolov5.classify import val as validate
from models.experimental import attempt_load from app.yolov5.models.experimental import attempt_load
from models.yolo import ClassificationModel, DetectionModel from app.yolov5.models.yolo import ClassificationModel, DetectionModel
from utils.dataloaders import create_classification_dataloader from app.yolov5.utils.dataloaders import create_classification_dataloader
from utils.general import (DATASETS_DIR, LOGGER, WorkingDirectory, check_git_status, check_requirements, colorstr, from app.yolov5.utils.general import (DATASETS_DIR, LOGGER, WorkingDirectory, check_git_status, check_requirements, colorstr,
download, increment_path, init_seeds, print_args, yaml_save) download, increment_path, init_seeds, print_args, yaml_save)
from utils.loggers import GenericLogger from app.yolov5.utils.loggers import GenericLogger
from utils.plots import imshow_cls from app.yolov5.utils.plots import imshow_cls
from utils.torch_utils import (ModelEMA, model_info, reshape_classifier_output, select_device, smart_DDP, from app.yolov5.utils.torch_utils import (ModelEMA, model_info, reshape_classifier_output, select_device, smart_DDP,
smart_optimizer, smartCrossEntropyLoss, torch_distributed_zero_first) smart_optimizer, smartCrossEntropyLoss, torch_distributed_zero_first)
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html

8
app/yolov5/classify/val.py
View File

@ -33,10 +33,10 @@ if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH sys.path.append(str(ROOT)) # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.common import DetectMultiBackend from app.yolov5.models.common import DetectMultiBackend
from utils.dataloaders import create_classification_dataloader from app.yolov5.utils.dataloaders import create_classification_dataloader
from utils.general import LOGGER, Profile, check_img_size, check_requirements, colorstr, increment_path, print_args from app.yolov5.utils.general import LOGGER, Profile, check_img_size, check_requirements, colorstr, increment_path, print_args
from utils.torch_utils import select_device, smart_inference_mode from app.yolov5.utils.torch_utils import select_device, smart_inference_mode
@smart_inference_mode() @smart_inference_mode()

0
app/yolov5/data_set/170111334447456256/results/HRF-622SS.1.txt
View File

0
app/yolov5/data_set/170111334447456256/results/HRF-622SS.txt
View File

0
app/yolov5/data_set/170111334447456256/results/HRF-718DS.txt
View File

0
app/yolov5/data_set/170111334447456256/results/HRF-718DW.txt
View File

14
app/yolov5/export.py
View File

@ -64,12 +64,12 @@ if str(ROOT) not in sys.path:
if platform.system() != 'Windows': if platform.system() != 'Windows':
ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
from models.experimental import attempt_load from app.yolov5.models.experimental import attempt_load
from models.yolo import ClassificationModel, Detect from app.yolov5.models.yolo import ClassificationModel, Detect
from utils.dataloaders import LoadImages from app.yolov5.utils.dataloaders import LoadImages
from utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_version, from app.yolov5.utils.general import (LOGGER, Profile, check_dataset, check_img_size, check_requirements, check_version,
check_yaml, colorstr, file_size, get_default_args, print_args, url2file) check_yaml, colorstr, file_size, get_default_args, print_args, url2file)
from utils.torch_utils import select_device, smart_inference_mode from app.yolov5.utils.torch_utils import select_device, smart_inference_mode
def export_formats(): def export_formats():
@ -309,7 +309,7 @@ def export_saved_model(model,
import tensorflow as tf import tensorflow as tf
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
from models.tf import TFModel from app.yolov5.models.tf import TFModel
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
f = str(file).replace('.pt', '_saved_model') f = str(file).replace('.pt', '_saved_model')
@ -371,7 +371,7 @@ def export_tflite(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=c
converter.target_spec.supported_types = [tf.float16] converter.target_spec.supported_types = [tf.float16]
converter.optimizations = [tf.lite.Optimize.DEFAULT] converter.optimizations = [tf.lite.Optimize.DEFAULT]
if int8: if int8:
from models.tf import representative_dataset_gen from app.yolov5.models.tf import representative_dataset_gen
dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False) dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False)
converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib=100) converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib=100)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8] converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]

12
app/yolov5/hubconf.py
View File

@ -28,12 +28,12 @@ def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbo
""" """
from pathlib import Path from pathlib import Path
from models.common import AutoShape, DetectMultiBackend from app.yolov5.models.common import AutoShape, DetectMultiBackend
from models.experimental import attempt_load from app.yolov5.models.experimental import attempt_load
from models.yolo import ClassificationModel, DetectionModel from app.yolov5.models.yolo import ClassificationModel, DetectionModel
from utils.downloads import attempt_download from app.yolov5.utils.downloads import attempt_download
from utils.general import LOGGER, check_requirements, intersect_dicts, logging from app.yolov5.utils.general import LOGGER, check_requirements, intersect_dicts, logging
from utils.torch_utils import select_device from app.yolov5.utils.torch_utils import select_device
if not verbose: if not verbose:
LOGGER.setLevel(logging.WARNING) LOGGER.setLevel(logging.WARNING)

2
app/yolov5/models/experimental.py
View File

@ -72,7 +72,7 @@ class Ensemble(nn.ModuleList):
def attempt_load(weights, device=None, inplace=True, fuse=True): def attempt_load(weights, device=None, inplace=True, fuse=True):
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
from models.yolo import Detect, Model from app.yolov5.models.yolo import Detect, Model
model = Ensemble() model = Ensemble()
for w in weights if isinstance(weights, list) else [weights]: for w in weights if isinstance(weights, list) else [weights]:

10
app/yolov5/models/tf.py
View File

@ -27,12 +27,12 @@ import torch
import torch.nn as nn import torch.nn as nn
from tensorflow import keras from tensorflow import keras
from models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv, from app.yolov5.models.common import (C3, SPP, SPPF, Bottleneck, BottleneckCSP, C3x, Concat, Conv, CrossConv, DWConv,
DWConvTranspose2d, Focus, autopad) DWConvTranspose2d, Focus, autopad)
from models.experimental import MixConv2d, attempt_load from app.yolov5.models.experimental import MixConv2d, attempt_load
from models.yolo import Detect from app.yolov5.models.yolo import Detect
from utils.activations import SiLU from app.yolov5.utils.activations import SiLU
from utils.general import LOGGER, make_divisible, print_args from app.yolov5.utils.general import LOGGER, make_divisible, print_args
class TFBN(keras.layers.Layer): class TFBN(keras.layers.Layer):

2
app/yolov5/train_server.py
View File

@ -462,7 +462,7 @@ def train(hyp, opt, device, data_list,id,callbacks): # hyp is path/to/hyp.yaml
# break # must break all DDP ranks # break # must break all DDP ranks
######实时传输训练精度参数############# ######实时传输训练精度参数#############
#gain_train_report(int(epoch + 1), float(results[0]), pro, version, epochs) #gain_train_report(int(epoch + 1), float(results[0]), pro, version, epochs)
report_cellback(epoch, epochs, float(results[0]),train_num) report_cellback(epoch, epochs, float(results[0]))
# end epoch ---------------------------------------------------------------------------------------------------- # end epoch ----------------------------------------------------------------------------------------------------
########训练数量和保存模型########### ########训练数量和保存模型###########
#save_train_report_result(pro, train_num, best) #save_train_report_result(pro, train_num, best)

2
app/yolov5/utils/downloads.py
View File

@ -64,7 +64,7 @@ def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'): def attempt_download(file, repo='ultralytics/yolov5', release='v6.2'):
# Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc. # Attempt file download from GitHub release assets if not found locally. release = 'latest', 'v6.2', etc.
from utils.general import LOGGER from app.yolov5.utils.general import LOGGER
def github_assets(repository, version='latest'): def github_assets(repository, version='latest'):
# Return GitHub repo tag (i.e. 'v6.2') and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...]) # Return GitHub repo tag (i.e. 'v6.2') and assets (i.e. ['yolov5s.pt', 'yolov5m.pt', ...])

2
app/yolov5/utils/torch_utils.py
View File

@ -64,7 +64,7 @@ def smart_DDP(model):
def reshape_classifier_output(model, n=1000): def reshape_classifier_output(model, n=1000):
# Update a TorchVision classification model to class count 'n' if required # Update a TorchVision classification model to class count 'n' if required
from models.common import Classify from app.yolov5.models.common import Classify
name, m = list((model.model if hasattr(model, 'model') else model).named_children())[-1] # last module name, m = list((model.model if hasattr(model, 'model') else model).named_children())[-1] # last module
if isinstance(m, Classify): # YOLOv5 Classify() head if isinstance(m, Classify): # YOLOv5 Classify() head
if m.linear.out_features != n: if m.linear.out_features != n:

BIN
app/yolov5/圆孔_123_RODY_1_640.zip
View File

Binary file not shown.