1. 程式人生 > >畫pytorch模型圖,以及引數計算

畫pytorch模型圖,以及引數計算

    剛入pytorch的坑,程式碼還沒看太懂。之前用keras用習慣了,第一次使用pytorch還有些不適應,希望廣大老司機多多指教。

    首先說說,我們如何視覺化模型。在keras中就一句話,keras.summary(),或者plot_model(),就可以把模型展現的淋漓盡致。

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。但是有網友提供了一段程式碼,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,上程式碼吧。

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("該層的結構:" + str(list(i.size())))
        for j in i.size():
            l *= j
        print("該層引數和:" + str(l))
        k = k + l
    print("總引數數量和:" + str(k))



    模型很簡單,程式碼也很簡單。就是conv -> relu -> maxpool -> conv -> relu -> maxpool -> fc

    大家在視覺化的時候,直接複製make_dot那段程式碼即可,然後需要初始化一個net,以及這個網路需要的資料規模,此處就以    這段程式碼為例,初始化一個模型net,準備這個模型的輸入資料x,shape為(batch,channels,height,width) 然後把資料傳入模型得到輸出結果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()
 


    最後輸出該網路的各種引數。

該層的結構:[16, 1, 5, 5]
該層引數和:400
該層的結構:[16]
該層引數和:16
該層的結構:[32, 16, 5, 5]
該層引數和:12800
該層的結構:[32]
該層引數和:32
該層的結構:[10, 1568]
該層引數和:15680
該層的結構:[10]
該層引數和:10
總引數數量和:28938
    打個廣告,新建的深度學習-語義分割的QQ群,歡迎加入:674968699.