def __init__( self, c1, c2, k=1, s=1, p=None, g=1, act=True, ): # ch_in, ch_out, kernel, stride, padding, groups assert isinstance( self.use_v3, bool), "You need to decide whether use_yolov3 is True or False" super(Conv, self).__init__() if isinstance(k, list): assert len(k) <= 2 and k[0] == k[-1] k = k[0] if isinstance(s, list): assert len(s) <= 2 and s[0] == s[-1] s = s[0] self.conv = nn.Conv(c1, c2, k, s, autopad(k, p), groups=g, bias=False) self.bn = nn.BatchNorm(c2) self.act = ( nn.LeakyReLU(0.1) if self.use_v3 else SiLU()) if act is True else ( act if isinstance(act, nn.Module) else nn.Identity())
def __init__(self): super(SpatialAttentionModule, self).__init__() self.conv2d = nn.Conv2d(in_channels=2, out_channels=1, kernel_size=7, stride=1, padding=3) self.act = SiLU()
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=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 'torchscript' in include: export_torchscript(model, img, file, optimize) if 'onnx' in include: export_onnx(model, img, file, opset, train, dynamic, simplify) if 'coreml' in include: export_coreml(model, img, file) # Finish print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')
def __init__(self, c1, reduction=16): super(ChannelAttentionModule, self).__init__() mid_channel = c1 // reduction self.avg_pool = nn.AdaptiveAvgPool2d(1) self.max_pool = nn.AdaptiveMaxPool2d(1) self.shared_MLP = nn.Sequential( nn.Linear(in_features=c1, out_features=mid_channel), nn.LeakyReLU(0.1, inplace=True), nn.Linear(in_features=mid_channel, out_features=c1)) # self.sigmoid = nn.Sigmoid() self.act = SiLU()
def load_model(weights, device): # Load model # model = attempt_load(weights, map_location=device) # load FP32 model with open('data/coco128.yaml') as f: data_dict = yaml.load(f, Loader=yaml.FullLoader) model = Model('models/yolov5s.yaml').to(device) model.names = data_dict['names'] model = model.fuse().eval() ckpt = torch.load(weights, map_location=device) ckpt['model'].float().fuse().eval() print({ k: (v.shape, model.state_dict()[k].shape) for k, v in ckpt['model'].float().state_dict().items() if model.state_dict()[k].shape != v.shape }) print({ k: (v.shape, ckpt['model'].float().state_dict()[k].shape) for k, v in model.state_dict().items() if ckpt['model'].float().state_dict()[k].shape != v.shape }) ckpt['model'] = { k: v for k, v in ckpt['model'].float().state_dict().items() if model.state_dict()[k].shape == v.shape } model.load_state_dict(ckpt['model'], strict=False) for k, m in model.named_modules(): m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatability if isinstance(m, Conv) and isinstance(m.act, nn.Hardswish): m.act = Hardswish() if isinstance(m, Conv) and isinstance(m.act, nn.SiLU): m.act = SiLU() return model
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', '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 int8=False, # CoreML/TF INT8 quantization dynamic=False, # ONNX/TF: dynamic axes simplify=False, # ONNX: simplify model opset=12, # ONNX: opset version verbose=False, # TensorRT: verbose log workspace=4, # TensorRT: workspace size (GB) 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 ): t = time.time() include = [x.lower() for x in include] tf_exports = list(x in include for x in ('saved_model', 'pb', 'tflite', 'tfjs')) # TensorFlow exports imgsz *= 2 if len(imgsz) == 1 else 1 # expand file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else 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, inplace=True, fuse=True) # load FP32 model nc, names = model.nc, model.names # number of classes, class names # 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 if half: im, model = im.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.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(im) # dry runs LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} ({file_size(file):.1f} MB)") # Exports if 'torchscript' in include: export_torchscript(model, im, file, optimize) if 'onnx' in include: export_onnx(model, im, file, opset, train, dynamic, simplify) if 'engine' in include: export_engine(model, im, file, train, half, simplify, workspace, verbose) if 'coreml' in include: export_coreml(model, im, file) # TensorFlow Exports if any(tf_exports): pb, tflite, tfjs = tf_exports[1:] assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.' model = export_saved_model(model, im, file, dynamic, tf_nms=tfjs, agnostic_nms=tfjs, topk_per_class=topk_per_class, topk_all=topk_all, conf_thres=conf_thres, iou_thres=iou_thres) # keras model if pb or tfjs: # pb prerequisite to tfjs export_pb(model, im, file) if tflite: export_tflite(model, im, file, int8=int8, data=data, ncalib=100) if tfjs: export_tfjs(model, im, file) # Finish LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)' f"\nResults saved to {colorstr('bold', file.parent.resolve())}" f'\nVisualize with https://netron.app')
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 optimize=False, # TorchScript: optimize for mobile int8=False, # CoreML/TF INT8 quantization dynamic=False, # ONNX/TF: dynamic axes simplify=False, # ONNX: simplify model opset=12, # 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 ): t = time.time() include = [x.lower() for x in include] tf_exports = list(x in include for x in ('saved_model', 'pb', 'tflite', 'edgetpu', 'tfjs')) # TensorFlow exports file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else 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, inplace=True, fuse=True) # load FP32 model nc, names = model.nc, model.names # number of classes, class names # Checks imgsz *= 2 if len(imgsz) == 1 else 1 # expand opset = 12 if ('openvino' in include) else opset # OpenVINO requires opset <= 12 assert nc == len(names), f'Model class count {nc} != len(names) {len(names)}' # 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 if half: im, model = im.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.SiLU): m.act = SiLU() elif isinstance(m, Detect): m.inplace = inplace m.onnx_dynamic = dynamic if hasattr(m, 'forward_export'): m.forward = m.forward_export # assign custom forward (optional) for _ in range(2): y = model(im) # dry runs shape = tuple(y[0].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 'torchscript' in include: f[0] = export_torchscript(model, im, file, optimize) if 'engine' in include: # TensorRT required before ONNX f[1] = export_engine(model, im, file, train, half, simplify, workspace, verbose) if ('onnx' in include) or ('openvino' in include): # OpenVINO requires ONNX f[2] = export_onnx(model, im, file, opset, train, dynamic, simplify) if 'openvino' in include: f[3] = export_openvino(model, im, file) if 'coreml' in include: _, f[4] = export_coreml(model, im, file) # TensorFlow Exports if any(tf_exports): pb, tflite, edgetpu, tfjs = tf_exports[1:] 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 and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.' model, f[5] = export_saved_model(model, 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, conf_thres=conf_thres, iou_thres=iou_thres) # keras model if pb or tfjs: # pb prerequisite to tfjs f[6] = export_pb(model, im, file) if tflite or edgetpu: f[7] = export_tflite(model, im, file, int8=int8 or edgetpu, data=data, ncalib=100) if edgetpu: f[8] = export_edgetpu(model, im, file) if tfjs: f[9] = export_tfjs(model, im, file) # Finish f = [str(x) for x in f if x] # filter out '' and None if any(f): LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)' f"\nResults saved to {colorstr('bold', file.parent.resolve())}" f"\nDetect: python detect.py --weights {f[-1]}" f"\nPyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')" f"\nValidate: python val.py --weights {f[-1]}" f"\nVisualize: https://netron.app") return f # return list of exported files/dirs
for x in opt.img_size] # verify img_size are gs-multiples print('opt:{}'.format(opt)) # Input img = torch.zeros(opt.batch_size, 3, *opt.img_size) # image size(1,3,320,192) iDetection # Update model for k, m in model.named_modules(): m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility if isinstance( m, models.common.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, models.yolo.Detect): # m.forward = m.forward_export # assign forward (optional) model.model[-1].export = True # set Detect() layer export=True y = model(img) # dry run # TorchScript export try: print('\nStarting TorchScript export with torch %s...' % torch.__version__) f = opt.weights.replace('.pt', '.torchscript.pt') # filename ts = torch.jit.trace(model, img) ts.save(f) print('TorchScript export success, saved as %s' % f) except Exception as e: print('TorchScript export failure: %s' % e)
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples # Input img = torch.zeros(opt.batch_size, 3, *opt.img_size) # image size(1,3,320,192) iDetection # Update model for k, m in model.named_modules(): m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility if isinstance( m, models.common.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, models.yolo.Detect): # m.forward = m.forward_export # assign forward (optional) if isinstance(m, models.common.ShuffleV2Block): #shufflenet block nn.SiLU for i in range(len(m.branch1)): if isinstance(m.branch1[i], nn.SiLU): m.branch1[i] = SiLU() for i in range(len(m.branch2)): if isinstance(m.branch2[i], nn.SiLU): m.branch2[i] = SiLU() model.model[-1].export = True # set Detect() layer export=True y = model(img) # dry run # ONNX export print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
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 # Load PyTorch model device = select_device(device) assert not ( device.type == 'cpu' and opt.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:') try: print( f'\n{prefix} starting export with torch {torch.__version__}...' ) f = weights.replace('.pt', '.torchscript.pt') # filename ts = torch.jit.trace(model, img, strict=False) (optimize_for_mobile(ts) if optimize else ts).save(f) print( f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)' ) except Exception as e: print(f'{prefix} export failure: {e}') # ONNX export ------------------------------------------------------------------------------------------------------ if 'onnx' in include: prefix = colorstr('ONNX:') try: import onnx print(f'{prefix} starting export with onnx {onnx.__version__}...') f = weights.replace('.pt', '.onnx') # filename torch.onnx.export( model, img, f, verbose=False, opset_version=opset_version, 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 # print(onnx.helper.printable_graph(model_onnx.graph)) # print # Simplify if simplify: try: check_requirements(['onnx-simplifier']) import onnxsim print( f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...' ) model_onnx, check = onnxsim.simplify( model_onnx, dynamic_input_shape=dynamic, input_shapes={'images': list(img.shape)} if dynamic else None) assert check, 'assert check failed' onnx.save(model_onnx, f) except Exception as e: print(f'{prefix} simplifier failure: {e}') print( f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)' ) except Exception as e: print(f'{prefix} export failure: {e}') # CoreML export ---------------------------------------------------------------------------------------------------- if 'coreml' in include: prefix = colorstr('CoreML:') try: import coremltools as ct print( f'{prefix} starting export with coremltools {ct.__version__}...' ) 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]) ]) f = weights.replace('.pt', '.mlmodel') # filename model.save(f) print( f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)' ) except Exception as e: print(f'{prefix} export failure: {e}') # Finish print( f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.' )