apoorva/greenhouse
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

updates

Browse Source
This commit is contained in:
Glenn Jocher
2019-10-07 00:50:47 +02:00
parent 58d510df52
commit 1a8bbf600d
3 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
utils/torch_utils.py
+13
View File
@@ -64,3 +64,16 @@ def fuse_conv_and_bn(conv, bn):
fusedconv.bias.copy_(b_conv + b_bn)
return fusedconv
def model_info(model, report='summary'):
# Plots a line-by-line description of a PyTorch model
n_p = sum(x.numel() for x in model.parameters()) # number parameters
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
if report is 'full':
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
for i, (name, p) in enumerate(model.named_parameters()):
name = name.replace('module_list.', '')
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
(i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
print('Model Summary: %g layers, %g parameters, %g gradients' % (len(list(model.parameters())), n_p, n_g))
utils/utils.py
-13
View File
@@ -41,19 +41,6 @@ def load_classes(path):
return list(filter(None, names)) # filter removes empty strings (such as last line)
def model_info(model, report='summary'):
# Plots a line-by-line description of a PyTorch model
n_p = sum(x.numel() for x in model.parameters()) # number parameters
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
if report is 'full':
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
for i, (name, p) in enumerate(model.named_parameters()):
name = name.replace('module_list.', '')
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
(i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
print('Model Summary: %g layers, %g parameters, %g gradients' % (len(list(model.parameters())), n_p, n_g))
def labels_to_class_weights(labels, nc=80):
# Get class weights (inverse frequency) from training labels
ni = len(labels) # number of images