剛?cè)雙ytorch的坑，代碼還沒看太懂。之前用keras用習(xí)慣了，第一次使用pytorch還有些不適應(yīng)，希望廣大老司機多多指教。

    首先說說，我們?nèi)绾慰梢暬Ｐ?。在keras中就一句話，keras.summary()，或者plot_model()，就可以把模型展現(xiàn)的淋漓盡致。

但是pytorch中好像沒有這樣一個api讓我們直觀的看到模型的樣子。但是有網(wǎng)友提供了一段代碼，可以把模型畫出來，對我來說簡直就是如有神助啊。話不多說，上代碼吧。

import torch
from torch.autograd import Variable
import torch.nn as nn
from graphviz import Digraph
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2)
)
self.conv2 = nn.Sequential(
nn.Conv2d(in_channels=16, out_channels=32, kernel_size=5, stride=1, padding=2),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2)
)
self.out = nn.Linear(32*7*7, 10)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = x.view(x.size(0), -1)  # (batch, 32*7*7)
out = self.out(x)
return out
def make_dot(var, params=None):
""" Produces Graphviz representation of PyTorch autograd graph
Blue nodes are the Variables that require grad, orange are Tensors
saved for backward in torch.autograd.Function
Args:
var: output Variable
params: dict of (name, Variable) to add names to node that
require grad (TODO: make optional)
"""
if params is not None:
assert isinstance(params.values()[0], Variable)
param_map = {id(v): k for k, v in params.items()}
node_attr = dict(style='filled',
shape='box',
align='left',
fontsize='12',
ranksep='0.1',
height='0.2')
dot = Digraph(node_attr=node_attr, graph_attr=dict(size="12,12"))
seen = set()
def size_to_str(size):
return '('+(', ').join(['%d' % v for v in size])+')'
def add_nodes(var):
if var not in seen:
if torch.is_tensor(var):
dot.node(str(id(var)), size_to_str(var.size()), fillcolor='orange')
elif hasattr(var, 'variable'):
u = var.variable
name = param_map[id(u)] if params is not None else ''
node_name = '%s\n %s' % (name, size_to_str(u.size()))
dot.node(str(id(var)), node_name, fillcolor='lightblue')
else:
dot.node(str(id(var)), str(type(var).__name__))
seen.add(var)
if hasattr(var, 'next_functions'):
for u in var.next_functions:
if u[0] is not None:
dot.edge(str(id(u[0])), str(id(var)))
add_nodes(u[0])
if hasattr(var, 'saved_tensors'):
for t in var.saved_tensors:
dot.edge(str(id(t)), str(id(var)))
add_nodes(t)
add_nodes(var.grad_fn)
return dot
if __name__ == '__main__':
net = CNN()
x = Variable(torch.randn(1, 1, 28, 28))
y = net(x)
g = make_dot(y)
g.view()
params = list(net.parameters())
k = 0
for i in params:
l = 1
print("該層的結(jié)構(gòu)：" + str(list(i.size())))
for j in i.size():
l *= j
print("該層參數(shù)和：" + str(l))
k = k + l
print("總參數(shù)數(shù)量和：" + str(k))

    大家在可視化的時候，直接復(fù)制make_dot那段代碼即可，然后需要初始化一個net，以及這個網(wǎng)絡(luò)需要的數(shù)據(jù)規(guī)模，此處就以    這段代碼為例，初始化一個模型net，準備這個模型的輸入數(shù)據(jù)x，shape為(batch，channels，height，width) 然后把數(shù)據(jù)傳入模型得到輸出結(jié)果y。傳入make_dot即可得到下圖。

net = CNN()
x = Variable(torch.randn(1, 1, 28, 28))
y = net(x)
g = make_dot(y)
g.view()

    最后輸出該網(wǎng)絡(luò)的各種參數(shù)。

該層的結(jié)構(gòu)：[16, 1, 5, 5]
該層參數(shù)和：400
該層的結(jié)構(gòu)：[16]
該層參數(shù)和：16
該層的結(jié)構(gòu)：[32, 16, 5, 5]
該層參數(shù)和：12800
該層的結(jié)構(gòu)：[32]
該層參數(shù)和：32
該層的結(jié)構(gòu)：[10, 1568]
該層參數(shù)和：15680
該層的結(jié)構(gòu)：[10]
該層參數(shù)和：10
總參數(shù)數(shù)量和：28938