Swapnil Sayan Saha
Swapnil Sayan Saha
I have similar issue. In my case, however, the dataset is a custom dataset which has been properly converted into .npy files. The input array to the fastgrnn model is...
Thanks a lot. That really helped. I have a few more questions @ShikharJ If X = (550,6), what should be XX be reshaped to (probably the decomposition is due to...
Can confirm I have the same error.
What I understood from trying to run anything apart from the USPS-10 tutorial given in the repo, even training the model for 1 epoch less (the USPS-10 fastgrnn model) causes...
@Darshcg how many subnets does it consider? all 10^19?
Sure I will let you know. I am using DuckieTag's bindings.
Tf version is tf2.9.2 (GPU)
Comment out the following lines in the file ```/home/name/miniconda3/envs/tf-2.13/lib/python3.9/site-packages/keras_flops/flops_registory.py``` ``` @ops.RegisterStatistics("AddV2", "flops") def _flops_add(graph, node): """inference is supportted""" return _binary_per_element_op_flops(graph, node) ``` The library works fine without these lines and...