Open ZhenmingYu opened 2 years ago
Running this gives:
File ".local/lib/python3.7/site-packages/decolle/lenet_decolle_model_fa.py", line 109, in build_conv_stack
readout = nn.FALinear(int(feature_height * feature_width * Nhid[i + 1]), out_channels)
AttributeError: module 'torch.nn' has no attribute 'FALinear'
I removed the "nn." in decolle/lenet_decolle_model_fa.py line 109 and it works.
Hi Clemens, I recommend using the branch update_21014. Do you get the same problem? I'll merge this into master soon.
Hey Emre, the branch you mentioned also has the same error, e.g. importing non-FA modules
and using nn.FALinear
Also, I am trying to rerun the numbers from the decolle paper (e.g. DVS gesture 4.46% error) the paper mentions a hyperparameter search, but I am not sure if that matches the hyperparameters in
(for example, the paper says burning 50ms and this config says 100 etc).
Any chance to get the hyperparameters used in the paper, or maybe even some pre-trained weights?
Was importing standard decolle rather than decolle_fa modules.