lji comments

Repositories
Issues
Comments

Results 5 comments of

lji

Can sparse network after compression do quanzation-aware training?

Hello, can anyone share some experiences?

Check failed: status == CUDNN_STATUS_SUCCESS (3 vs. 0) CUDNN_STATUS_BAD_PARAM

It may be helpful to specify the GPU id.

Concern about the performance

@yarkable Do you get the expected gain with 2X times training？

Stuck when running "python3 train.py"

@karansomaiah Use `tf.global_variables_initializer` instead. /home/liuji/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py:97: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense...

The multi-scale testing issues

@JiaminWoo You can check the accuracy to verify it.