Skip to content
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

Jump to bottom

Add size information #21

Merged
merged 1 commit into from
Aug 9, 2018
Merged

Add size information #21

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
23 changes: 18 additions & 5 deletions torchsummary/torchsummary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,9 +3,9 @@
from torch.autograd import Variable

from collections import OrderedDict
import numpy as np


def summary(model, input_size, device="cuda"):
def summary(model, input_size, batch_size=-1,device="cuda"):
def register_hook(module):
def hook(module, input, output):
class_name = str(module.__class__).split('.')[-1].split("'")[0]
Expand All @@ -14,12 +14,12 @@ def hook(module, input, output):
m_key = '%s-%i' % (class_name, module_idx+1)
summary[m_key] = OrderedDict()
summary[m_key]['input_shape'] = list(input[0].size())
summary[m_key]['input_shape'][0] = -1
summary[m_key]['input_shape'][0] = batch_size
if isinstance(output, (list,tuple)):
summary[m_key]['output_shape'] = [[-1] + list(o.size())[1:] for o in output]
else:
summary[m_key]['output_shape'] = list(output.size())
summary[m_key]['output_shape'][0] = -1
summary[m_key]['output_shape'][0] = batch_size

params = 0
if hasattr(module, 'weight') and hasattr(module.weight, 'size'):
Expand Down Expand Up @@ -67,18 +67,31 @@ def hook(module, input, output):
print(line_new)
print('================================================================')
total_params = 0
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']
print(line_new)
#assume 4 bytes/number (float on cuda).
total_input_size = abs(np.prod(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_size = total_params_size + total_output_size + total_input_size

print('================================================================')
print('Total params: {0:,}'.format(total_params))
print('Trainable params: {0:,}'.format(trainable_params))
print('Non-trainable params: {0:,}'.format(total_params - trainable_params))
print('----------------------------------------------------------------')
# return summary
print('Input size (MB): %0.2f' % total_input_size)
print('Forward/backward pass size (MB): %0.2f' % total_output_size)
print('Params size (MB): %0.2f' % total_params_size)
print('Estimated Total Size (MB): %0.2f' % total_size)
print('----------------------------------------------------------------')
#return summary