Hello,
l tried the following and l get stuck at visualizing the features of my model.
my_model=torch.load(my_pre_trained_mode)
my_model.keys()
['cnn.conv0.weight',
'cnn.conv0.bias',
'cnn.conv1.weight',
'cnn.conv1.bias',
'cnn.conv2.weight',
'cnn.conv2.bias',
'cnn.batchnorm2.weight',
'cnn.batchnorm2.bias',
'cnn.batchnorm2.running_mean',
'cnn.batchnorm2.running_var',
'cnn.conv3.weight',
'cnn.conv3.bias',
'cnn.conv4.weight',
'cnn.conv4.bias',
'cnn.batchnorm4.weight',
'cnn.batchnorm4.bias',
'cnn.batchnorm4.running_mean',
'cnn.batchnorm4.running_var',
'cnn.conv5.weight',
'cnn.conv5.bias',
'cnn.conv6.weight',
'cnn.conv6.bias',
'cnn.batchnorm6.weight',
'cnn.batchnorm6.bias',
'cnn.batchnorm6.running_mean',
'cnn.batchnorm6.running_var',
'rnn.0.rnn.weight_ih_l0',
'rnn.0.rnn.weight_hh_l0',
'rnn.0.rnn.bias_ih_l0',
'rnn.0.rnn.bias_hh_l0',
'rnn.0.rnn.weight_ih_l0_reverse',
'rnn.0.rnn.weight_hh_l0_reverse',
'rnn.0.rnn.bias_ih_l0_reverse',
'rnn.0.rnn.bias_hh_l0_reverse',
'rnn.0.embedding.weight',
'rnn.0.embedding.bias',
'rnn.1.rnn.weight_ih_l0',
'rnn.1.rnn.weight_hh_l0',
'rnn.1.rnn.bias_ih_l0',
'rnn.1.rnn.bias_hh_l0',
'rnn.1.rnn.weight_ih_l0_reverse',
'rnn.1.rnn.weight_hh_l0_reverse',
'rnn.1.rnn.bias_ih_l0_reverse',
'rnn.1.rnn.bias_hh_l0_reverse',
'rnn.1.embedding.weight',
'rnn.1.embedding.bias']
conv0=my_moel.get('cnn.conv0.weight')
...
(63,0 ,.,.) =
0.5229 -1.4523 1.0662
0.1048 -1.8494 1.5810
-0.4727 -1.4437 1.9553
[torch.FloatTensor of size 64x1x3x3]
rnn=my_mode.get('rnn.1.embedding.weight')
[torch.FloatTensor of size 37x512]
How can l visualize the weights of each layer for instance cnn.conv0 and rnn.1 ?
Thank you