shreydixit/fmri-stimulus-image-reconstruction-using-biggan

Hi! I'm Shrey Dixit and I'm a an MSc student studying Intelligent Adaptive Systems at the University of Hamburg

I am an MSc student studying Intelligent Adaptive Systems at the University of Hamburg. I focus on Deep Learning and Computational Neuroscience. Currently I'm working as a Research Assistant at ICNS, Hamburg where I am developing and using msapy for Explainable AI and Brain Network Analysis

Connect with me:

fmri-stimulus-image-reconstruction-using-biggan's Issues

Test

How can we test the data?

Train problem

Hi,shreyDixit, there is a problem when training:

Traceback (most recent call last):-------------------------------------------------------------------------------| 0.00% [0/19 00:00<00:00]
  File "train.py", line 19, in <module>
    learn.fit_one_cycle(4, 3e-2)
  File "/opt/conda/lib/python3.6/site-packages/fastai/train.py", line 23, in fit_one_cycle
    learn.fit(cyc_len, max_lr, wd=wd, callbacks=callbacks)
  File "/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py", line 200, in fit
    fit(epochs, self, metrics=self.metrics, callbacks=self.callbacks+callbacks)
  File "/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py", line 101, in fit
    loss = loss_batch(learn.model, xb, yb, learn.loss_func, learn.opt, cb_handler)
  File "/opt/conda/lib/python3.6/site-packages/fastai/basic_train.py", line 30, in loss_batch
    loss = loss_func(out, *yb)
  File "/home/fMRI-Stimulus-Image-Reconstruction-using-BigGAN-main/utils.py", line 53, in __call__
    input_features = self.truncated_vgg19(input)
  File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/container.py", line 141, in forward
    input = module(input)
  File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 446, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
    self.padding, self.dilation, self.groups)
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

Thanks for your time