Unverified 提交 442a7abd authored 作者: Glenn Jocher's avatar Glenn Jocher 提交者: GitHub

Refactor `export.py` (#4080)

* Refactor `export.py` * cleanup * Update check_requirements() * Update export.py
上级 0cc7c587
...@@ -24,74 +24,29 @@ from utils.general import colorstr, check_img_size, check_requirements, file_siz ...@@ -24,74 +24,29 @@ from utils.general import colorstr, check_img_size, check_requirements, file_siz
from utils.torch_utils import select_device from utils.torch_utils import select_device
def run(weights='./yolov5s.pt', # weights path def export_torchscript(model, img, file, optimize):
img_size=(640, 640), # image (height, width) # TorchScript model export
batch_size=1, # batch size
device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
include=('torchscript', 'onnx', 'coreml'), # include formats
half=False, # FP16 half-precision export
inplace=False, # set YOLOv5 Detect() inplace=True
train=False, # model.train() mode
optimize=False, # TorchScript: optimize for mobile
dynamic=False, # ONNX: dynamic axes
simplify=False, # ONNX: simplify model
opset_version=12, # ONNX: opset version
):
t = time.time()
include = [x.lower() for x in include]
img_size *= 2 if len(img_size) == 1 else 1 # expand
# Load PyTorch model
device = select_device(device)
assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
model = attempt_load(weights, map_location=device) # load FP32 model
labels = model.names
# Input
gs = int(max(model.stride)) # grid size (max stride)
img_size = [check_img_size(x, gs) for x in img_size] # verify img_size are gs-multiples
img = torch.zeros(batch_size, 3, *img_size).to(device) # image size(1,3,320,192) iDetection
# Update model
if half:
img, model = img.half(), model.half() # to FP16
model.train() if train else model.eval() # training mode = no Detect() layer grid construction
for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if isinstance(m, Conv): # assign export-friendly activations
if isinstance(m.act, nn.Hardswish):
m.act = Hardswish()
elif isinstance(m.act, nn.SiLU):
m.act = SiLU()
elif isinstance(m, Detect):
m.inplace = inplace
m.onnx_dynamic = dynamic
# m.forward = m.forward_export # assign forward (optional)
for _ in range(2):
y = model(img) # dry runs
print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)")
# TorchScript export -----------------------------------------------------------------------------------------------
if 'torchscript' in include or 'coreml' in include:
prefix = colorstr('TorchScript:') prefix = colorstr('TorchScript:')
try: try:
print(f'\n{prefix} starting export with torch {torch.__version__}...') print(f'\n{prefix} starting export with torch {torch.__version__}...')
f = weights.replace('.pt', '.torchscript.pt') # filename f = file.with_suffix('.torchscript.pt')
ts = torch.jit.trace(model, img, strict=False) ts = torch.jit.trace(model, img, strict=False)
(optimize_for_mobile(ts) if optimize else ts).save(f) (optimize_for_mobile(ts) if optimize else ts).save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
return ts
except Exception as e: except Exception as e:
print(f'{prefix} export failure: {e}') print(f'{prefix} export failure: {e}')
# ONNX export ------------------------------------------------------------------------------------------------------
if 'onnx' in include: def export_onnx(model, img, file, opset_version, train, dynamic, simplify):
# ONNX model export
prefix = colorstr('ONNX:') prefix = colorstr('ONNX:')
try: try:
check_requirements(('onnx', 'onnx-simplifier'))
import onnx import onnx
print(f'{prefix} starting export with onnx {onnx.__version__}...') print(f'{prefix} starting export with onnx {onnx.__version__}...')
f = weights.replace('.pt', '.onnx') # filename f = file.with_suffix('.onnx')
torch.onnx.export(model, img, f, verbose=False, opset_version=opset_version, torch.onnx.export(model, img, f, verbose=False, opset_version=opset_version,
training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL, training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not train, do_constant_folding=not train,
...@@ -109,7 +64,6 @@ def run(weights='./yolov5s.pt', # weights path ...@@ -109,7 +64,6 @@ def run(weights='./yolov5s.pt', # weights path
# Simplify # Simplify
if simplify: if simplify:
try: try:
check_requirements(['onnx-simplifier'])
import onnxsim import onnxsim
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
...@@ -125,21 +79,79 @@ def run(weights='./yolov5s.pt', # weights path ...@@ -125,21 +79,79 @@ def run(weights='./yolov5s.pt', # weights path
except Exception as e: except Exception as e:
print(f'{prefix} export failure: {e}') print(f'{prefix} export failure: {e}')
# CoreML export ----------------------------------------------------------------------------------------------------
if 'coreml' in include: def export_coreml(ts_model, img, file, train):
# CoreML model export
prefix = colorstr('CoreML:') prefix = colorstr('CoreML:')
try: try:
import coremltools as ct import coremltools as ct
print(f'{prefix} starting export with coremltools {ct.__version__}...') print(f'{prefix} starting export with coremltools {ct.__version__}...')
f = file.with_suffix('.mlmodel')
assert train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`' assert train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`'
model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])]) model = ct.convert(ts_model, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
f = weights.replace('.pt', '.mlmodel') # filename
model.save(f) model.save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e: except Exception as e:
print(f'{prefix} export failure: {e}') print(f'{prefix} export failure: {e}')
def run(weights='./yolov5s.pt', # weights path
img_size=(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', 'coreml'), # include formats
half=False, # FP16 half-precision export
inplace=False, # set YOLOv5 Detect() inplace=True
train=False, # model.train() mode
optimize=False, # TorchScript: optimize for mobile
dynamic=False, # ONNX: dynamic axes
simplify=False, # ONNX: simplify model
opset_version=12, # ONNX: opset version
):
t = time.time()
include = [x.lower() for x in include]
img_size *= 2 if len(img_size) == 1 else 1 # expand
file = Path(weights)
# Load PyTorch model
device = select_device(device)
assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
model = attempt_load(weights, map_location=device) # load FP32 model
names = model.names
# Input
gs = int(max(model.stride)) # grid size (max stride)
img_size = [check_img_size(x, gs) for x in img_size] # verify img_size are gs-multiples
img = torch.zeros(batch_size, 3, *img_size).to(device) # image size(1,3,320,192) iDetection
# Update model
if half:
img, model = img.half(), model.half() # to FP16
model.train() if train else model.eval() # training mode = no Detect() layer grid construction
for k, m in model.named_modules():
if isinstance(m, Conv): # assign export-friendly activations
if isinstance(m.act, nn.Hardswish):
m.act = Hardswish()
elif isinstance(m.act, nn.SiLU):
m.act = SiLU()
elif isinstance(m, Detect):
m.inplace = inplace
m.onnx_dynamic = dynamic
# m.forward = m.forward_export # assign forward (optional)
for _ in range(2):
y = model(img) # dry runs
print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)")
# Exports
if 'onnx' in include:
export_onnx(model, img, file, opset_version, train, dynamic, simplify)
if 'torchscript' in include or 'coreml' in include:
ts = export_torchscript(model, img, file, optimize)
if 'coreml' in include:
export_coreml(ts, img, file, train)
# Finish # Finish
print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.') print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论