KWS-demo throwing errors on running FastGRNNCUDA inference on google speech commands dataset

[IannoIITR]

Error message:- Exception in thread Thread-1: Traceback (most recent call last): File "/anaconda/envs/spr/lib/python3.6/threading.py", line 916, in _bootstrap_inner self.run() File "kws-demo.py", line 151, in run logits = fastgrnn(torch.FloatTensor(features)) File "/anaconda/envs/spr/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/mnt/batch/tasks/shared/LS_root/mounts/clusters/noida/code/Users/ian.noronha01/Microsoft/EdgeML/examples/pytorch/FastCells/KWS-training/edgeml_pytorch/trainer/fastmodel.py", line 190, in forward model_output = self.hidden2keyword(model_output[-1, :, :]) File "/anaconda/envs/spr/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/anaconda/envs/spr/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 87, in forward return F.linear(input, self.weight, self.bias) File "/anaconda/envs/spr/lib/python3.6/site-packages/torch/nn/functional.py", line 1370, in linear ret = torch.addmm(bias, input, weight.t()) RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_addmm

If I run it on a CPU then it throws an error that FastGRNNCUDA is only supported for GPU devices and using the solution from a previous closed issue #232 throws unexpected layers error File "kws-demo.py", line 203, in <module> fastgrnn.load_state_dict(torch.load(fastgrnn_model_path, map_location=torch.device('cpu'))) File "/anaconda/envs/spr/lib/python3.6/site-packages/torch/nn/modules/module.py", line 830, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for RNNClassifierModel: Missing key(s) in state_dict: "rnn_list.0.cell.W", "rnn_list.0.cell.U", "rnn_list.0.cell.bias_gate", "rnn_list.0.cell.bias_update", "rnn_list.0.cell.zeta", "rnn_list.0.cell.nu", "rnn_list.0.unrollRNN.RNNCell.W", "rnn_list.0.unrollRNN.RNNCell.U", "rnn_list.0.unrollRNN.RNNCell.bias_gate", "rnn_list.0.unrollRNN.RNNCell.bias_update", "rnn_list.0.unrollRNN.RNNCell.zeta", "rnn_list.0.unrollRNN.RNNCell.nu", "rnn_list.1.cell.W", "rnn_list.1.cell.U", "rnn_list.1.cell.bias_gate", "rnn_list.1.cell.bias_update", "rnn_list.1.cell.zeta", "rnn_list.1.cell.nu", "rnn_l

[ShikharJ]

@SachinG007 Can you please take a look?