Dr. Aditi Panda

@samhallman I am having this same problem. The pre-trained model is not accessible. Kindly help.

Also while trying to run the demo with the command: _python faster_rcnn/demo.py --model ~/tf_deformable_net/restore_output/Resnet50_iter_145000.ckpt_, I get this error: **Traceback (most recent call last): File "faster_rcnn/demo.py", line 21, in from lib.networks.factory...

I can't find these files either. Even init.py doesnot work because lenet is absent. Are we just supposed to comment everything that's absent ?

> i added this command (--expt-relaxed-constexpr) after which line has nvcc. the error disappear. > eg, > nvcc -std=c++11 -c -o roi_pooling_op.cu.o roi_pooling_op_gpu.cu.cc > -I $TF_INC -I $NSYNC_INC -D GOOGLE_CUDA=1...

@MrXieJ what changes did you do in make.sh?

I'm facing the same problem. Please help.

@bodhid44 Thanks, I found the dataset, but yet to run it. What about the other datasets used in other chapters? @pradod the dataset is not accessible anymore. Can you help?

@StTu @smudge1872 Were you able to find out what was wrong? Is this solved? Please help.

I am new to Caffe, and am also facing this problem. I read in another git thread (https://github.com/alexgkendall/caffe-segnet/issues/57#issuecomment-276044793) that calling caffe.reset_all() might help, but have no idea where to place...

In https://github.com/s9xie/hed/issues/14, @yhlleo suggested to change the cuDNN version from v4 to v3. I am using v7. What's the solution? Do I have to downgrade to a lower version of...