Skip to content

Multi-gpu compatibility: torch-summary for 'cuda:1' and so on #93

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 2 commits into
base: master
Choose a base branch
from
Open

Multi-gpu compatibility: torch-summary for 'cuda:1' and so on #93

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
50a229e
add multi-gpus torch-summary capability
Sep 21, 2019
a52f625
multi-gpu compatible: torch-summary for cuda:1 and so on
Sep 21, 2019
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
138 changes: 73 additions & 65 deletions torchsummary/torchsummary.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,75 +41,83 @@ def hook(module, input, output):
):
hooks.append(module.register_forward_hook(hook))

device = device.lower()
assert device in [
"cuda",
"cpu",
], "Input device is not valid, please specify 'cuda' or 'cpu'"

if device == "cuda" and torch.cuda.is_available():
dtype = torch.cuda.FloatTensor
else:
dtype = torch.FloatTensor
if(isinstance(device, str)):
device.lower()
# torch parse function that returns an object of type: torch.device. argument can be passed as a torch.device object, a string('cuda:1') or integer device index(1)
device=torch._C._nn._parse_to(device)[0]

# multiple inputs to the network
if isinstance(input_size, tuple):
input_size = [input_size]

# batch_size of 2 for batchnorm
x = [torch.rand(2, *in_size).type(dtype) for in_size in input_size]
# print(type(x[0]))

# create properties
summary = OrderedDict()
hooks = []

# register hook
model.apply(register_hook)

# make a forward pass
# print(x.shape)
model(*x)

# remove these hooks
for h in hooks:
h.remove()

print("----------------------------------------------------------------")
line_new = "{:>20} {:>25} {:>15}".format("Layer (type)", "Output Shape", "Param #")
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)
try:
if (device == torch.device('cuda')):
if(torch.cuda.is_available()):
x = [torch.rand(2, *in_size).to('cuda') for in_size in input_size]
else:
raise Exception("No CUDA-capable device detected.")
elif not (device == torch.device('cpu') or device == torch.device('cpu:0')):
with torch.cuda.device(device):
if(torch.cuda.is_available()):
x = [torch.rand(2, *in_size).to(device) for in_size in input_size]
except RuntimeError:
raise Exception("Specified device either doesn't exist or is not CUDA-capable. ") from None
else:
if (device == torch.device('cpu') or device == torch.device('cpu:0')):
x = [torch.rand(2, *in_size).to('cpu') for in_size in input_size]
# print(type(x[0]))

# create properties
summary = OrderedDict()
hooks = []

# 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("----------------------------------------------------------------")
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
# register hook
model.apply(register_hook)

# make a forward pass
# print(x.shape)
model(*x)

# remove these hooks
for h in hooks:
h.remove()

print("----------------------------------------------------------------")
line_new = "{:>20} {:>25} {:>15}".format("Layer (type)", "Output Shape", "Param #")
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("----------------------------------------------------------------")
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