Captcha Break Versions Save

由于模型定义在 Jupyter Notebook 中，PyTorch 无法直接加载模型代码，所以加载模型之前需要先定义模型，如：

import torch
import torch.nn as nn


class Model(nn.Module):
    def __init__(self, n_classes, input_shape=(3, 64, 128)):
        super(Model, self).__init__()
        self.input_shape = input_shape
        channels = [32, 64, 128, 256, 256]
        layers = [2, 2, 2, 2, 2]
        kernels = [3, 3, 3, 3, 3]
        pools = [2, 2, 2, 2, (2, 1)]
        modules = OrderedDict()
        
        def cba(name, in_channels, out_channels, kernel_size):
            modules[f'conv{name}'] = nn.Conv2d(in_channels, out_channels, kernel_size,
                                               padding=(1, 1) if kernel_size == 3 else 0)
            modules[f'bn{name}'] = nn.BatchNorm2d(out_channels)
            modules[f'relu{name}'] = nn.ReLU(inplace=True)
        
        last_channel = 3
        for block, (n_channel, n_layer, n_kernel, k_pool) in enumerate(zip(channels, layers, kernels, pools)):
            for layer in range(1, n_layer + 1):
                cba(f'{block+1}{layer}', last_channel, n_channel, n_kernel)
                last_channel = n_channel
            modules[f'pool{block + 1}'] = nn.MaxPool2d(k_pool)
        modules[f'dropout'] = nn.Dropout(0.25, inplace=True)
        
        self.cnn = nn.Sequential(modules)
        self.lstm = nn.LSTM(input_size=self.infer_features(), hidden_size=128, num_layers=2, bidirectional=True)
        self.fc = nn.Linear(in_features=256, out_features=n_classes)
    
    def infer_features(self):
        x = torch.zeros((1,)+self.input_shape)
        x = self.cnn(x)
        x = x.reshape(x.shape[0], -1, x.shape[-1])
        return x.shape[1]

    def forward(self, x):
        x = self.cnn(x)
        x = x.reshape(x.shape[0], -1, x.shape[-1])
        x = x.permute(2, 0, 1)
        x, _ = self.lstm(x)
        x = self.fc(x)
        return x

model = torch.load('ctc.pth')

CNN 模型总体准确率是 98.26% CTC 模型总体准确率是 99.21%