Ankle/yolov5_ZWgra
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

Refactor models/export.py arguments (#3564)

Browse Source 
* Refactor models/export.py arguments

* cleanup

* cleanup
This commit is contained in:
Glenn Jocher authored and GitHub committed 2021-06-09 22:43:46 +02:00
1 parent 66cf5c28c1
commit 0e5cfdbea7
1 file changed
+63 -45
Download Patch File Download Diff File Expand all files Collapse all files
models/export.py
+63 -45
View File
@@ -1,4 +1,4 @@
"""Exports a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats """Export a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats
Usage: Usage:
$ python path/to/models/export.py --weights yolov5s.pt --img 640 --batch 1 $ python path/to/models/export.py --weights yolov5s.pt --img 640 --batch 1
@@ -21,42 +21,39 @@ from utils.activations import Hardswish, SiLU
from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging
from utils.torch_utils import select_device from utils.torch_utils import select_device
if __name__ == '__main__':
parser = argparse.ArgumentParser() def export(weights='./yolov5s.pt', # weights path
parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path') img_size=(640, 640), # image (height, width)
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width batch_size=1, # batch size
parser.add_argument('--batch-size', type=int, default=1, help='batch size') device='cpu', # cuda device, i.e. 0 or 0,1,2,3 or cpu
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') include=('torchscript', 'onnx', 'coreml'), # include formats
parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats') half=False, # FP16 half-precision export
parser.add_argument('--half', action='store_true', help='FP16 half-precision export') inplace=False, # set YOLOv5 Detect() inplace=True
parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') train=False, # model.train() mode
parser.add_argument('--train', action='store_true', help='model.train() mode') optimize=False, # TorchScript: optimize for mobile
parser.add_argument('--optimize', action='store_true', help='optimize TorchScript for mobile') # TorchScript-only dynamic=False, # ONNX: dynamic axes
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') # ONNX-only simplify=False, # ONNX: simplify model
parser.add_argument('--simplify', action='store_true', help='simplify ONNX model') # ONNX-only opset_version=12, # ONNX: opset version
parser.add_argument('--opset-version', type=int, default=12, help='ONNX opset version') # ONNX-only ):
opt = parser.parse_args()
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
opt.include = [x.lower() for x in opt.include]
print(opt)
set_logging()
t = time.time() t = time.time()
include = [x.lower() for x in include]
img_size *= 2 if len(img_size) == 1 else 1 # expand
# Load PyTorch model # Load PyTorch model
device = select_device(opt.device) device = select_device(device)
assert not (opt.device.lower() == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0' assert not (device.type == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0'
model = attempt_load(opt.weights, map_location=device) # load FP32 model model = attempt_load(weights, map_location=device) # load FP32 model
labels = model.names labels = model.names
# Input # Input
gs = int(max(model.stride)) # grid size (max stride) gs = int(max(model.stride)) # grid size (max stride)
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples img_size = [check_img_size(x, gs) for x in img_size] # verify img_size are gs-multiples
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection img = torch.zeros(batch_size, 3, *img_size).to(device) # image size(1,3,320,192) iDetection
# Update model # Update model
if opt.half: if half:
img, model = img.half(), model.half() # to FP16 img, model = img.half(), model.half() # to FP16
model.train() if opt.train else model.eval() # training mode = no Detect() layer grid construction model.train() if train else model.eval() # training mode = no Detect() layer grid construction
for k, m in model.named_modules(): for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if isinstance(m, models.common.Conv): # assign export-friendly activations if isinstance(m, models.common.Conv): # assign export-friendly activations
@@ -65,42 +62,42 @@ if __name__ == '__main__':
elif isinstance(m.act, nn.SiLU): elif isinstance(m.act, nn.SiLU):
m.act = SiLU() m.act = SiLU()
elif isinstance(m, models.yolo.Detect): elif isinstance(m, models.yolo.Detect):
m.inplace = opt.inplace m.inplace = inplace
m.onnx_dynamic = opt.dynamic m.onnx_dynamic = dynamic
# m.forward = m.forward_export # assign forward (optional) # m.forward = m.forward_export # assign forward (optional)
for _ in range(2): for _ in range(2):
y = model(img) # dry runs y = model(img) # dry runs
print(f"\n{colorstr('PyTorch:')} starting from {opt.weights} ({file_size(opt.weights):.1f} MB)") print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)")
# TorchScript export ----------------------------------------------------------------------------------------------- # TorchScript export -----------------------------------------------------------------------------------------------
if 'torchscript' in opt.include or 'coreml' in opt.include: 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 = opt.weights.replace('.pt', '.torchscript.pt') # filename f = weights.replace('.pt', '.torchscript.pt') # filename
ts = torch.jit.trace(model, img, strict=False) ts = torch.jit.trace(model, img, strict=False)
(optimize_for_mobile(ts) if opt.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)')
except Exception as e: except Exception as e:
print(f'{prefix} export failure: {e}') print(f'{prefix} export failure: {e}')
# ONNX export ------------------------------------------------------------------------------------------------------ # ONNX export ------------------------------------------------------------------------------------------------------
if 'onnx' in opt.include: if 'onnx' in include:
prefix = colorstr('ONNX:') prefix = colorstr('ONNX:')
try: try:
import onnx import onnx
print(f'{prefix} starting export with onnx {onnx.__version__}...') print(f'{prefix} starting export with onnx {onnx.__version__}...')
f = opt.weights.replace('.pt', '.onnx') # filename f = weights.replace('.pt', '.onnx') # filename
torch.onnx.export(model, img, f, verbose=False, opset_version=opt.opset_version, torch.onnx.export(model, img, f, verbose=False, opset_version=opset_version,
training=torch.onnx.TrainingMode.TRAINING if opt.train else torch.onnx.TrainingMode.EVAL, training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not opt.train, do_constant_folding=not train,
input_names=['images'], input_names=['images'],
output_names=['output'], output_names=['output'],
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640) dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640)
'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85) 'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85)
} if opt.dynamic else None) } if dynamic else None)
# Checks # Checks
model_onnx = onnx.load(f) # load onnx model model_onnx = onnx.load(f) # load onnx model
@@ -108,7 +105,7 @@ if __name__ == '__main__':
# print(onnx.helper.printable_graph(model_onnx.graph)) # print # print(onnx.helper.printable_graph(model_onnx.graph)) # print
# Simplify # Simplify
if opt.simplify: if simplify:
try: try:
check_requirements(['onnx-simplifier']) check_requirements(['onnx-simplifier'])
import onnxsim import onnxsim
@@ -116,8 +113,8 @@ if __name__ == '__main__':
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
model_onnx, check = onnxsim.simplify( model_onnx, check = onnxsim.simplify(
model_onnx, model_onnx,
dynamic_input_shape=opt.dynamic, dynamic_input_shape=dynamic,
input_shapes={'images': list(img.shape)} if opt.dynamic else None) input_shapes={'images': list(img.shape)} if dynamic else None)
assert check, 'assert check failed' assert check, 'assert check failed'
onnx.save(model_onnx, f) onnx.save(model_onnx, f)
except Exception as e: except Exception as e:
@@ -127,15 +124,15 @@ if __name__ == '__main__':
print(f'{prefix} export failure: {e}') print(f'{prefix} export failure: {e}')
# CoreML export ---------------------------------------------------------------------------------------------------- # CoreML export ----------------------------------------------------------------------------------------------------
if 'coreml' in opt.include: if 'coreml' in include:
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__}...')
assert opt.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, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
f = opt.weights.replace('.pt', '.mlmodel') # filename 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:
@@ -143,3 +140,24 @@ if __name__ == '__main__':
# 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.')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path')
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image (height, width)')
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats')
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('--optimize', action='store_true', help='TorchScript: optimize for mobile')
parser.add_argument('--dynamic', action='store_true', help='ONNX: dynamic axes')
parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
parser.add_argument('--opset-version', type=int, default=12, help='ONNX: opset version')
opt = parser.parse_args()
print(opt)
set_logging()
export(**vars(opt))