622 lines
29 KiB
Python
622 lines
29 KiB
Python
# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
|
|
"""
|
|
Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit
|
|
|
|
Format | `export.py --include` | Model
|
|
--- | --- | ---
|
|
PyTorch | - | yolov5s.pt
|
|
TorchScript | `torchscript` | yolov5s.torchscript
|
|
ONNX | `onnx` | yolov5s.onnx
|
|
OpenVINO | `openvino` | yolov5s_openvino_model/
|
|
TensorRT | `engine` | yolov5s.engine
|
|
CoreML | `coreml` | yolov5s.mlmodel
|
|
TensorFlow SavedModel | `saved_model` | yolov5s_saved_model/
|
|
TensorFlow GraphDef | `pb` | yolov5s.pb
|
|
TensorFlow Lite | `tflite` | yolov5s.tflite
|
|
TensorFlow Edge TPU | `edgetpu` | yolov5s_edgetpu.tflite
|
|
TensorFlow.js | `tfjs` | yolov5s_web_model/
|
|
|
|
Requirements:
|
|
$ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu # CPU
|
|
$ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow # GPU
|
|
|
|
Usage:
|
|
$ python export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
|
|
|
|
Inference:
|
|
$ python detect.py --weights yolov5s.pt # PyTorch
|
|
yolov5s.torchscript # TorchScript
|
|
yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn
|
|
yolov5s.xml # OpenVINO
|
|
yolov5s.engine # TensorRT
|
|
yolov5s.mlmodel # CoreML (macOS-only)
|
|
yolov5s_saved_model # TensorFlow SavedModel
|
|
yolov5s.pb # TensorFlow GraphDef
|
|
yolov5s.tflite # TensorFlow Lite
|
|
yolov5s_edgetpu.tflite # TensorFlow Edge TPU
|
|
|
|
TensorFlow.js:
|
|
$ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
|
|
$ npm install
|
|
$ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
|
|
$ npm start
|
|
"""
|
|
|
|
import argparse
|
|
import json
|
|
import os
|
|
import platform
|
|
import subprocess
|
|
import sys
|
|
import time
|
|
import warnings
|
|
from pathlib import Path
|
|
|
|
import pandas as pd
|
|
import torch
|
|
import yaml
|
|
from torch.utils.mobile_optimizer import optimize_for_mobile
|
|
|
|
FILE = Path(__file__).resolve()
|
|
ROOT = FILE.parents[0] # 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.experimental import attempt_load
|
|
from app.yolov5.models.yolo import ClassificationModel, Detect
|
|
from app.yolov5.utils.dataloaders import LoadImages
|
|
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)
|
|
from app.yolov5.utils.torch_utils import select_device, smart_inference_mode
|
|
|
|
|
|
def export_formats():
|
|
# YOLOv5 export formats
|
|
x = [
|
|
['PyTorch', '-', '.pt', True, True],
|
|
['TorchScript', 'torchscript', '.torchscript', True, True],
|
|
['ONNX', 'onnx', '.onnx', True, True],
|
|
['OpenVINO', 'openvino', '_openvino_model', True, False],
|
|
['TensorRT', 'engine', '.engine', False, True],
|
|
['CoreML', 'coreml', '.mlmodel', True, False],
|
|
['TensorFlow SavedModel', 'saved_model', '_saved_model', True, True],
|
|
['TensorFlow GraphDef', 'pb', '.pb', True, True],
|
|
['TensorFlow Lite', 'tflite', '.tflite', True, False],
|
|
['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite', False, False],
|
|
['TensorFlow.js', 'tfjs', '_web_model', False, False],]
|
|
return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix', 'CPU', 'GPU'])
|
|
|
|
|
|
def try_export(inner_func):
|
|
# YOLOv5 export decorator, i..e @try_export
|
|
inner_args = get_default_args(inner_func)
|
|
|
|
def outer_func(*args, **kwargs):
|
|
prefix = inner_args['prefix']
|
|
try:
|
|
with Profile() as dt:
|
|
f, model = inner_func(*args, **kwargs)
|
|
LOGGER.info(f'{prefix} export success ✅ {dt.t:.1f}s, saved as {f} ({file_size(f):.1f} MB)')
|
|
return f, model
|
|
except Exception as e:
|
|
LOGGER.info(f'{prefix} export failure ❌ {dt.t:.1f}s: {e}')
|
|
return None, None
|
|
|
|
return outer_func
|
|
|
|
|
|
@try_export
|
|
def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
|
|
# YOLOv5 TorchScript model export
|
|
LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
|
|
f = file.with_suffix('.torchscript')
|
|
|
|
ts = torch.jit.trace(model, im, strict=False)
|
|
|
|
d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names}
|
|
extra_files = {'config.txt': json.dumps(d)} # torch._C.ExtraFilesMap()
|
|
if optimize: # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
|
|
optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files)
|
|
else:
|
|
#ts.save(str(f), _extra_files=extra_files)
|
|
#重命名，解决中文乱码
|
|
save_dir = os.path.dirname(f)
|
|
tmp_file = os.path.join(save_dir, f"temp_{time.time()}.pt")
|
|
ts.save(tmp_file)
|
|
|
|
if os.path.exists(f):
|
|
os.remove(f)
|
|
os.rename(tmp_file, f)
|
|
else:
|
|
os.rename(tmp_file, f)
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
|
|
# YOLOv5 ONNX export
|
|
check_requirements(('onnx',))
|
|
import onnx
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
|
|
f = file.with_suffix('.onnx')
|
|
|
|
torch.onnx.export(
|
|
model.cpu() if dynamic else model, # --dynamic only compatible with cpu
|
|
im.cpu() if dynamic else im,
|
|
f,
|
|
verbose=False,
|
|
opset_version=opset,
|
|
training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
|
|
do_constant_folding=not train,
|
|
input_names=['images'],
|
|
output_names=['output'],
|
|
dynamic_axes={
|
|
'images': {
|
|
0: 'batch',
|
|
2: 'height',
|
|
3: 'width'}, # shape(1,3,640,640)
|
|
'output': {
|
|
0: 'batch',
|
|
1: 'anchors'} # shape(1,25200,85)
|
|
} if dynamic else None)
|
|
|
|
# Checks
|
|
model_onnx = onnx.load(f) # load onnx model
|
|
onnx.checker.check_model(model_onnx) # check onnx model
|
|
|
|
# Metadata
|
|
d = {'stride': int(max(model.stride)), 'names': model.names}
|
|
for k, v in d.items():
|
|
meta = model_onnx.metadata_props.add()
|
|
meta.key, meta.value = k, str(v)
|
|
onnx.save(model_onnx, f)
|
|
|
|
# Simplify
|
|
if simplify:
|
|
try:
|
|
cuda = torch.cuda.is_available()
|
|
check_requirements(('onnxruntime-gpu' if cuda else 'onnxruntime', 'onnx-simplifier>=0.4.1'))
|
|
import onnxsim
|
|
|
|
LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
|
|
model_onnx, check = onnxsim.simplify(model_onnx)
|
|
assert check, 'assert check failed'
|
|
onnx.save(model_onnx, f)
|
|
except Exception as e:
|
|
LOGGER.info(f'{prefix} simplifier failure: {e}')
|
|
return f, model_onnx
|
|
|
|
|
|
@try_export
|
|
def export_openvino(model, file, half, prefix=colorstr('OpenVINO:')):
|
|
# YOLOv5 OpenVINO export
|
|
check_requirements(('openvino-dev',)) # requires openvino-dev: https://pypi.org/project/openvino-dev/
|
|
import openvino.inference_engine as ie
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...')
|
|
f = str(file).replace('.pt', f'_openvino_model{os.sep}')
|
|
|
|
cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f} --data_type {'FP16' if half else 'FP32'}"
|
|
subprocess.check_output(cmd.split()) # export
|
|
with open(Path(f) / file.with_suffix('.yaml').name, 'w') as g:
|
|
yaml.dump({'stride': int(max(model.stride)), 'names': model.names}, g) # add metadata.yaml
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_coreml(model, im, file, int8, half, prefix=colorstr('CoreML:')):
|
|
# YOLOv5 CoreML export
|
|
check_requirements(('coremltools',))
|
|
import coremltools as ct
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
|
|
f = file.with_suffix('.mlmodel')
|
|
|
|
ts = torch.jit.trace(model, im, strict=False) # TorchScript model
|
|
ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
|
|
bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None)
|
|
if bits < 32:
|
|
if platform.system() == 'Darwin': # quantization only supported on macOS
|
|
with warnings.catch_warnings():
|
|
warnings.filterwarnings("ignore", category=DeprecationWarning) # suppress numpy==1.20 float warning
|
|
ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
|
|
else:
|
|
print(f'{prefix} quantization only supported on macOS, skipping...')
|
|
ct_model.save(f)
|
|
return f, ct_model
|
|
|
|
|
|
@try_export
|
|
def export_engine(model, im, file, half, dynamic, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
|
|
# YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
|
|
assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
|
|
try:
|
|
import tensorrt as trt
|
|
except Exception:
|
|
if platform.system() == 'Linux':
|
|
check_requirements(('nvidia-tensorrt',), cmds=('-U --index-url https://pypi.ngc.nvidia.com',))
|
|
import tensorrt as trt
|
|
|
|
if trt.__version__[0] == '7': # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
|
|
grid = model.model[-1].anchor_grid
|
|
model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
|
|
export_onnx(model, im, file, 12, False, dynamic, simplify) # opset 12
|
|
model.model[-1].anchor_grid = grid
|
|
else: # TensorRT >= 8
|
|
check_version(trt.__version__, '8.0.0', hard=True) # require tensorrt>=8.0.0
|
|
export_onnx(model, im, file, 13, False, dynamic, simplify) # opset 13
|
|
onnx = file.with_suffix('.onnx')
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
|
|
assert onnx.exists(), f'failed to export ONNX file: {onnx}'
|
|
f = file.with_suffix('.engine') # TensorRT engine file
|
|
logger = trt.Logger(trt.Logger.INFO)
|
|
if verbose:
|
|
logger.min_severity = trt.Logger.Severity.VERBOSE
|
|
|
|
builder = trt.Builder(logger)
|
|
config = builder.create_builder_config()
|
|
config.max_workspace_size = workspace * 1 << 30
|
|
# config.set_memory_pool_limit(trt.MemoryPoolType.WORKSPACE, workspace << 30) # fix TRT 8.4 deprecation notice
|
|
|
|
flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
|
|
network = builder.create_network(flag)
|
|
parser = trt.OnnxParser(network, logger)
|
|
if not parser.parse_from_file(str(onnx)):
|
|
raise RuntimeError(f'failed to load ONNX file: {onnx}')
|
|
|
|
inputs = [network.get_input(i) for i in range(network.num_inputs)]
|
|
outputs = [network.get_output(i) for i in range(network.num_outputs)]
|
|
LOGGER.info(f'{prefix} Network Description:')
|
|
for inp in inputs:
|
|
LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}')
|
|
for out in outputs:
|
|
LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}')
|
|
|
|
if dynamic:
|
|
if im.shape[0] <= 1:
|
|
LOGGER.warning(f"{prefix}WARNING: --dynamic model requires maximum --batch-size argument")
|
|
profile = builder.create_optimization_profile()
|
|
for inp in inputs:
|
|
profile.set_shape(inp.name, (1, *im.shape[1:]), (max(1, im.shape[0] // 2), *im.shape[1:]), im.shape)
|
|
config.add_optimization_profile(profile)
|
|
|
|
LOGGER.info(f'{prefix} building FP{16 if builder.platform_has_fast_fp16 and half else 32} engine in {f}')
|
|
if builder.platform_has_fast_fp16 and half:
|
|
config.set_flag(trt.BuilderFlag.FP16)
|
|
with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
|
|
t.write(engine.serialize())
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_saved_model(model,
|
|
im,
|
|
file,
|
|
dynamic,
|
|
tf_nms=False,
|
|
agnostic_nms=False,
|
|
topk_per_class=100,
|
|
topk_all=100,
|
|
iou_thres=0.45,
|
|
conf_thres=0.25,
|
|
keras=False,
|
|
prefix=colorstr('TensorFlow SavedModel:')):
|
|
# YOLOv5 TensorFlow SavedModel export
|
|
import tensorflow as tf
|
|
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
|
|
|
|
from app.yolov5.models.tf import TFModel
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
|
f = str(file).replace('.pt', '_saved_model')
|
|
batch_size, ch, *imgsz = list(im.shape) # BCHW
|
|
|
|
tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
|
|
im = tf.zeros((batch_size, *imgsz, ch)) # BHWC order for TensorFlow
|
|
_ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
|
|
inputs = tf.keras.Input(shape=(*imgsz, ch), batch_size=None if dynamic else batch_size)
|
|
outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
|
|
keras_model = tf.keras.Model(inputs=inputs, outputs=outputs)
|
|
keras_model.trainable = False
|
|
keras_model.summary()
|
|
if keras:
|
|
keras_model.save(f, save_format='tf')
|
|
else:
|
|
spec = tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype)
|
|
m = tf.function(lambda x: keras_model(x)) # full model
|
|
m = m.get_concrete_function(spec)
|
|
frozen_func = convert_variables_to_constants_v2(m)
|
|
tfm = tf.Module()
|
|
tfm.__call__ = tf.function(lambda x: frozen_func(x)[:4] if tf_nms else frozen_func(x)[0], [spec])
|
|
tfm.__call__(im)
|
|
tf.saved_model.save(tfm,
|
|
f,
|
|
options=tf.saved_model.SaveOptions(experimental_custom_gradients=False) if check_version(
|
|
tf.__version__, '2.6') else tf.saved_model.SaveOptions())
|
|
return f, keras_model
|
|
|
|
|
|
@try_export
|
|
def export_pb(keras_model, file, prefix=colorstr('TensorFlow GraphDef:')):
|
|
# YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
|
|
import tensorflow as tf
|
|
from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
|
f = file.with_suffix('.pb')
|
|
|
|
m = tf.function(lambda x: keras_model(x)) # full model
|
|
m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
|
|
frozen_func = convert_variables_to_constants_v2(m)
|
|
frozen_func.graph.as_graph_def()
|
|
tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_tflite(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')):
|
|
# YOLOv5 TensorFlow Lite export
|
|
import tensorflow as tf
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
|
|
batch_size, ch, *imgsz = list(im.shape) # BCHW
|
|
f = str(file).replace('.pt', '-fp16.tflite')
|
|
|
|
converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
|
|
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
|
|
converter.target_spec.supported_types = [tf.float16]
|
|
converter.optimizations = [tf.lite.Optimize.DEFAULT]
|
|
if int8:
|
|
from app.yolov5.models.tf import representative_dataset_gen
|
|
dataset = LoadImages(check_dataset(check_yaml(data))['train'], img_size=imgsz, auto=False)
|
|
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_types = []
|
|
converter.inference_input_type = tf.uint8 # or tf.int8
|
|
converter.inference_output_type = tf.uint8 # or tf.int8
|
|
converter.experimental_new_quantizer = True
|
|
f = str(file).replace('.pt', '-int8.tflite')
|
|
if nms or agnostic_nms:
|
|
converter.target_spec.supported_ops.append(tf.lite.OpsSet.SELECT_TF_OPS)
|
|
|
|
tflite_model = converter.convert()
|
|
open(f, "wb").write(tflite_model)
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_edgetpu(file, prefix=colorstr('Edge TPU:')):
|
|
# YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
|
|
cmd = 'edgetpu_compiler --version'
|
|
help_url = 'https://coral.ai/docs/edgetpu/compiler/'
|
|
assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
|
|
if subprocess.run(f'{cmd} >/dev/null', shell=True).returncode != 0:
|
|
LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
|
|
sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0 # sudo installed on system
|
|
for c in (
|
|
'curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
|
|
'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
|
|
'sudo apt-get update', 'sudo apt-get install edgetpu-compiler'):
|
|
subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
|
|
ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
|
|
f = str(file).replace('.pt', '-int8_edgetpu.tflite') # Edge TPU model
|
|
f_tfl = str(file).replace('.pt', '-int8.tflite') # TFLite model
|
|
|
|
cmd = f"edgetpu_compiler -s -d -k 10 --out_dir {file.parent} {f_tfl}"
|
|
subprocess.run(cmd.split(), check=True)
|
|
return f, None
|
|
|
|
|
|
@try_export
|
|
def export_tfjs(file, prefix=colorstr('TensorFlow.js:')):
|
|
# YOLOv5 TensorFlow.js export
|
|
check_requirements(('tensorflowjs',))
|
|
import re
|
|
|
|
import tensorflowjs as tfjs
|
|
|
|
LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
|
|
f = str(file).replace('.pt', '_web_model') # js dir
|
|
f_pb = file.with_suffix('.pb') # *.pb path
|
|
f_json = f'{f}/model.json' # *.json path
|
|
|
|
cmd = f'tensorflowjs_converter --input_format=tf_frozen_model ' \
|
|
f'--output_node_names=Identity,Identity_1,Identity_2,Identity_3 {f_pb} {f}'
|
|
subprocess.run(cmd.split())
|
|
|
|
json = Path(f_json).read_text()
|
|
with open(f_json, 'w') as j: # sort JSON Identity_* in ascending order
|
|
subst = re.sub(
|
|
r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
|
|
r'"Identity.?.?": {"name": "Identity.?.?"}, '
|
|
r'"Identity.?.?": {"name": "Identity.?.?"}, '
|
|
r'"Identity.?.?": {"name": "Identity.?.?"}}}', r'{"outputs": {"Identity": {"name": "Identity"}, '
|
|
r'"Identity_1": {"name": "Identity_1"}, '
|
|
r'"Identity_2": {"name": "Identity_2"}, '
|
|
r'"Identity_3": {"name": "Identity_3"}}}', json)
|
|
j.write(subst)
|
|
return f, None
|
|
|
|
|
|
@smart_inference_mode()
|
|
def run(
|
|
data=ROOT / 'data/coco128.yaml', # 'dataset.yaml path'
|
|
weights=ROOT / 'yolov5s.pt', # weights path
|
|
imgsz=(640, 640), # image (height, width)
|
|
batch_size=1, # batch size
|
|
device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
|
|
include=('torchscript', 'onnx'), # include formats
|
|
half=False, # FP16 half-precision export
|
|
inplace=False, # set YOLOv5 Detect() inplace=True
|
|
train=False, # model.train() mode
|
|
keras=False, # use Keras
|
|
optimize=False, # TorchScript: optimize for mobile
|
|
int8=False, # CoreML/TF INT8 quantization
|
|
dynamic=False, # ONNX/TF/TensorRT: dynamic axes
|
|
simplify=False, # ONNX: simplify model
|
|
opset=11, # ONNX: opset version
|
|
verbose=False, # TensorRT: verbose log
|
|
workspace=4, # TensorRT: workspace size (GB)
|
|
nms=False, # TF: add NMS to model
|
|
agnostic_nms=False, # TF: add agnostic NMS to model
|
|
topk_per_class=100, # TF.js NMS: topk per class to keep
|
|
topk_all=100, # TF.js NMS: topk for all classes to keep
|
|
iou_thres=0.45, # TF.js NMS: IoU threshold
|
|
conf_thres=0.25, # TF.js NMS: confidence threshold
|
|
):
|
|
print(include)
|
|
t = time.time()
|
|
include = [x.lower() for x in include] # to lowercase
|
|
print(include)
|
|
fmts = tuple(export_formats()['Argument'][1:]) # --include arguments
|
|
print(fmts)
|
|
flags = [x in include for x in fmts]
|
|
assert sum(flags) == len(include), f'ERROR: Invalid --include {include}, valid --include arguments are {fmts}'
|
|
jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = flags # export booleans
|
|
file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights) # PyTorch weights
|
|
|
|
# Load PyTorch model
|
|
device = select_device(device)
|
|
if half:
|
|
assert device.type != 'cpu' or coreml, '--half only compatible with GPU export, i.e. use --device 0'
|
|
assert not dynamic, '--half not compatible with --dynamic, i.e. use either --half or --dynamic but not both'
|
|
model = attempt_load(weights, device=device, inplace=True, fuse=True) # load FP32 model
|
|
|
|
# Checks
|
|
imgsz *= 2 if len(imgsz) == 1 else 1 # expand
|
|
if optimize:
|
|
assert device.type == 'cpu', '--optimize not compatible with cuda devices, i.e. use --device cpu'
|
|
|
|
# Input
|
|
gs = int(max(model.stride)) # grid size (max stride)
|
|
imgsz = [check_img_size(x, gs) for x in imgsz] # verify img_size are gs-multiples
|
|
im = torch.zeros(batch_size, 3, *imgsz).to(device) # image size(1,3,320,192) BCHW iDetection
|
|
|
|
# Update model
|
|
model.train() if train else model.eval() # training mode = no Detect() layer grid construction
|
|
for k, m in model.named_modules():
|
|
if isinstance(m, Detect):
|
|
m.inplace = inplace
|
|
m.dynamic = dynamic
|
|
m.export = True
|
|
|
|
for _ in range(2):
|
|
y = model(im) # dry runs
|
|
if half and not coreml:
|
|
im, model = im.half(), model.half() # to FP16
|
|
shape = tuple((y[0] if isinstance(y, tuple) else y).shape) # model output shape
|
|
LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)")
|
|
|
|
# Exports
|
|
f = [''] * 10 # exported filenames
|
|
warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning) # suppress TracerWarning
|
|
if jit:
|
|
f[0], _ = export_torchscript(model, im, file, optimize)
|
|
if engine: # TensorRT required before ONNX
|
|
f[1], _ = export_engine(model, im, file, half, dynamic, simplify, workspace, verbose)
|
|
if onnx or xml: # OpenVINO requires ONNX
|
|
f[2], _ = export_onnx(model, im, file, opset, train, dynamic, simplify)
|
|
if xml: # OpenVINO
|
|
f[3], _ = export_openvino(model, file, half)
|
|
if coreml:
|
|
f[4], _ = export_coreml(model, im, file, int8, half)
|
|
|
|
# TensorFlow Exports
|
|
if any((saved_model, pb, tflite, edgetpu, tfjs)):
|
|
if int8 or edgetpu: # TFLite --int8 bug https://github.com/ultralytics/yolov5/issues/5707
|
|
check_requirements(('flatbuffers==1.12',)) # required before `import tensorflow`
|
|
assert not tflite or not tfjs, 'TFLite and TF.js models must be exported separately, please pass only one type.'
|
|
assert not isinstance(model, ClassificationModel), 'ClassificationModel export to TF formats not yet supported.'
|
|
f[5], model = export_saved_model(model.cpu(),
|
|
im,
|
|
file,
|
|
dynamic,
|
|
tf_nms=nms or agnostic_nms or tfjs,
|
|
agnostic_nms=agnostic_nms or tfjs,
|
|
topk_per_class=topk_per_class,
|
|
topk_all=topk_all,
|
|
iou_thres=iou_thres,
|
|
conf_thres=conf_thres,
|
|
keras=keras)
|
|
if pb or tfjs: # pb prerequisite to tfjs
|
|
f[6], _ = export_pb(model, file)
|
|
if tflite or edgetpu:
|
|
f[7], _ = export_tflite(model, im, file, int8 or edgetpu, data=data, nms=nms, agnostic_nms=agnostic_nms)
|
|
if edgetpu:
|
|
f[8], _ = export_edgetpu(file)
|
|
if tfjs:
|
|
f[9], _ = export_tfjs(file)
|
|
|
|
# Finish
|
|
f = [str(x) for x in f if x] # filter out '' and None
|
|
if any(f):
|
|
h = '--half' if half else '' # --half FP16 inference arg
|
|
LOGGER.info(f'\nExport complete ({time.time() - t:.1f}s)'
|
|
f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
|
|
f"\nDetect: python detect.py --weights {f[-1]} {h}"
|
|
f"\nValidate: python val.py --weights {f[-1]} {h}"
|
|
f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')"
|
|
f"\nVisualize: https://netron.app")
|
|
return f # return list of exported files/dirs
|
|
|
|
|
|
def parse_opt(weights,device):
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
|
|
parser.add_argument('--weights', nargs='+', type=str, default=weights, help='model.pt path(s)')
|
|
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
|
|
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
|
parser.add_argument('--device', default=device, help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
|
parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
|
|
parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
|
|
parser.add_argument('--train', action='store_true', help='model.train() mode')
|
|
parser.add_argument('--keras', action='store_true', help='TF: use Keras')
|
|
parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
|
|
parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
|
|
parser.add_argument('--dynamic', action='store_true', help='ONNX/TF/TensorRT: dynamic axes')
|
|
parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
|
|
parser.add_argument('--opset', type=int, default=11, help='ONNX: opset version')
|
|
parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log')
|
|
parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)')
|
|
parser.add_argument('--nms', action='store_true', help='TF: add NMS to model')
|
|
parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model')
|
|
parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
|
|
parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
|
|
parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
|
|
parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
|
|
parser.add_argument('--include',
|
|
nargs='+',
|
|
default=['torchscript','onnx'],
|
|
help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs')
|
|
opt = parser.parse_args()
|
|
print_args(vars(opt))
|
|
return opt
|
|
|
|
|
|
def main(opt):
|
|
for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]):
|
|
f = run(**vars(opt))
|
|
return f
|
|
|
|
def Start_Model_Export(weights,device):
|
|
# 判断cpu or gpu
|
|
if device == 'gpu':
|
|
device = '0'
|
|
else:
|
|
device = 'cpu'
|
|
opt = parse_opt(weights,device)
|
|
f = main(opt)
|
|
return f
|
|
|
|
|
|
if __name__ == "__main__":
|
|
weights = 'E:/aicheck/yolov5/zdp_R-ODYv1.pt'
|
|
device = 'gpu'
|
|
Start_Model_Export(weights,device)
|