search

dhlab-epfl / dhSegment

Generic framework for historical document processing
https://dhlab-epfl.github.com/dhSegment
GNU General Public License v3.0
370 stars 116 forks source link

Model loading/training error #22

Closed lvaleriu closed 5 years ago

lvaleriu commented 5 years ago

When executing the following command: python train.py with demo/demo_config.json I get this error. FYI I've followed the installation instructions with conda.

InternalError (see above for traceback): cuDNN launch failure : input shape([1,3,1095,538]) filter shape([7,7,3,64]) [[{{node resnet_v1_50/conv1/Conv2D}} = Conv2D[T=DT_FLOAT, data_format="NCHW", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 2, 2], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](gradients/resnet_v1_50/conv1/Conv2D_grad/Conv2DBackpropFilter-0-TransposeNHWCToNCHW-LayoutOptimizer, resnet_v1_50/conv1/weights/read)]]

solivr commented 5 years ago

This looks like you need to upgrade your cuDNN library or downgrade your tensorflow library. I would recommend changing tensorflow to v1.11 or v1.10.

lvaleriu commented 5 years ago

Ok. I’ll try that and come back to you. Thanks!

solivr commented 5 years ago

Closing because of inactivity.