Skip to content

Fixed params count and input size for multiple inputs #71

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fixed params count and input size for multiple inputs #71

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 7 additions & 9 deletions torchsummary/torchsummary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
import torch
import torch.nn as nn
import funcy
from torch.autograd import Variable

from collections import OrderedDict
Expand Down Expand Up @@ -79,27 +80,23 @@ def hook(module, input, output):
line_new = "{:>20} {:>25} {:>15}".format("Layer (type)", "Output Shape", "Param #")
print(line_new)
print("================================================================")
total_params = 0
total_params = sum(p.numel() for p in model.parameters())
trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
total_output = 0
trainable_params = 0
for layer in summary:
# input_shape, output_shape, trainable, nb_params
line_new = "{:>20} {:>25} {:>15}".format(
layer,
str(summary[layer]["output_shape"]),
"{0:,}".format(summary[layer]["nb_params"]),
)
total_params += summary[layer]["nb_params"]
total_output += np.prod(summary[layer]["output_shape"])
if "trainable" in summary[layer]:
if summary[layer]["trainable"] == True:
trainable_params += summary[layer]["nb_params"]
total_output += np.prod(list(funcy.flatten(summary[layer]["output_shape"])))
print(line_new)

# assume 4 bytes/number (float on cuda).
total_input_size = abs(np.prod(input_size) * batch_size * 4. / (1024 ** 2.))
total_input_size = abs(sum([np.prod(input_item) for input_item in input_size]) * batch_size * 4. / (1024 ** 2.))
total_output_size = abs(2. * total_output * 4. / (1024 ** 2.)) # x2 for gradients
total_params_size = abs(total_params.numpy() * 4. / (1024 ** 2.))
total_params_size = abs(total_params * 4. / (1024 ** 2.))
total_size = total_params_size + total_output_size + total_input_size

print("================================================================")
Expand All @@ -113,3 +110,4 @@ def hook(module, input, output):
print("Estimated Total Size (MB): %0.2f" % total_size)
print("----------------------------------------------------------------")
# return summary