search

ry / tensorflow-resnet

ResNet model in TensorFlow
MIT License
1.66k stars 625 forks source link

Bug in ResNet forward.py #2

Open hamidpalangi opened 8 years ago

hamidpalangi commented 8 years ago

Thanks for the great work @ry .

I am trying to use your converted TF models. I just tried "forward.py" but got the following RunTime error:

RuntimeError: NodeDef mentions attr 'data_format' not in Op<name=Conv2D; signature=input:T, filter:T -> output:T; attr=T:type,allowed=[DT_FLOAT, DT_DOUBLE]; attr=strides:list(int); attr=use_cudnn_on_gpu:bool,default=true; attr=padding:string,allowed=["SAME", "VALID"]>; NodeDef: import/conv1/conv = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 2, 2, 1], use_cudnn_on_gpu=true, _device="/device:CPU:0"](import/preprocess/centered_bgr, import/conv1/kernel)
^CWe've got an error while stopping in post-mortem: <type 'exceptions.KeyboardInterrupt'>

I tried all 3 TF models but got the same error. I checked the downloaded files and they were downloaded fully and correctly. Can you please help?

Thanks much! Hamid

gaxler commented 8 years ago

Had the same problem. I assume it's due to tfmodel been generated on older version of TF IMO this is a relevant issue. https://github.com/tensorflow/tensorflow/issues/1528

I'll try to convert the Caffe models on the newest version of TF. Hopefully this will solve the problem

hamidpalangi commented 8 years ago

Thanks much gaxler! Would it be possible to share your converted models to TF? For some reason I can not install Caffe on my machine ...

Thanks! Hamid