Aditya Kusupati
Aditya Kusupati
@SachinG007 please incorporate the changes from #173 for the fixing of optimizer for FC. Earlier gradient updates were not happening for FC due to some convention mismatch. Please look at...
@SachinG007 any updates on this PR?
I will try to set it up next week and test it out. @metastableB and @harsha-simhadri any thoughts? I think this is important for tf 2.0 transition.
@punitvara , a couple of things 1) Bonsai example runs fine, but FastCells don't 2) Can you isolate the changes you made from the original files, this diff is very...
@sridhargopinath can you look at this.
@sridhargopinath
It was because of the reorg - https://github.com/microsoft/EdgeML/blob/harsha/reorg/pytorch/edgeml_pytorch/trainer/fastTrainer.py
@harsha-simhadri thanks for the response. I will do the needful and @SachinG007 will assist me. I think we need to change the names of the new files (both the trainer...
- [ ] Arg parse should contain at least: dataDir, cellType, inputDims, hiddenDims, numEpochs, batchSize, learningRate, wRank, uRank, wSparsity, uSparsity, gate and update non-linearities, decayStep, decayRate and outputFile. Please follow...
hi @meetdoshi90, This is very useful and seems correct. Thanks for the contribution. However, I think the TF bonsai version is obsolete due to its old dependencies. I think more...