貌似新版的getmodel的参数改了？

[saaak]

net = get_model(net_name, pretrained_base=True, classes=classes) classes参数应该是int类型的？

[FossilDaddy]

我训练也报错了，不知道是不是这个原因 ** File "/Users/fossil/Downloads/Safety-Helmet-Wearing-Dataset-master/train_yolo.py", line 324, in net = get_model(net_name, pretrained_base=True, classes=classes) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/model_zoo.py", line 343, in get_model net = _modelsname File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/yolo3.py", line 602, in yolo3_darknet53_voc pretrained=pretrained_base, norm_layer=norm_layer, norm_kwargs=norm_kwargs, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/darknet.py", line 183, in darknet53 return get_darknet('v3', 53, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/darknet.py", line 161, in get_darknet 'darknet%d'%(num_layers), tag=pretrained, root=root), ctx=ctx) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mxnet/gluon/block.py", line 410, in load_parameters params[name]._load_init(loaded[name], ctx, cast_dtype=cast_dtype, dtype_source=dtype_source) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mxnet/gluon/parameter.py", line 279, in _load_init self.name, str(self.shape), str(data.shape)) AssertionError: Failed loading Parameter 'darknetv30_dense0_bias' from saved params: shape incompatible expected (['hat', 'person'],) vs saved (1000,) **

[Monkeone]

请问您解决了吗？

[Monkeone]

@njvisionpower

[FaresEmb]

请问您解决了吗？@FossilDaddy

[M1SAK1TN]

我训练也报错了，不知道是不是这个原因 ** File "/Users/fossil/Downloads/Safety-Helmet-Wearing-Dataset-master/train_yolo.py", line 324, in net = get_model(net_name, pretrained_base=True, classes=classes) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/model_zoo.py", line 343, in get_model net = _modelsname File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/yolo3.py", line 602, in yolo3_darknet53_voc pretrained=pretrained_base, norm_layer=norm_layer, norm_kwargs=norm_kwargs, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/darknet.py", line 183, in darknet53 return get_darknet('v3', 53, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/gluoncv/model_zoo/yolo/darknet.py", line 161, in get_darknet 'darknet%d'%(num_layers), tag=pretrained, root=root), ctx=ctx) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mxnet/gluon/block.py", line 410, in load_parameters params[name]._load_init(loaded[name], ctx, cast_dtype=cast_dtype, dtype_source=dtype_source) File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/mxnet/gluon/parameter.py", line 279, in _load_init self.name, str(self.shape), str(data.shape)) AssertionError: Failed loading Parameter 'darknetv30_dense0_bias' from saved params: shape incompatible expected (['hat', 'person'],) vs saved (1000,) **

我也是这个报错，求问有没有解决方法？？？

[gengyanlei]

net = get_model(net_name, pretrained_base=True) # , classes=len(classes) 去掉这个classes参数即可