model.py

import torch
import torch.nn as nn
import torchvision.models as models


class EncoderCNN(nn.Module):
    def __init__(self, embed_size):
        super(EncoderCNN, self).__init__()
        '''
        resnet = models.resnet50(pretrained=True)
        for param in resnet.parameters():
            param.requires_grad_(False)
        
        modules = list(resnet.children())[:-1]
        self.resnet = nn.Sequential(*modules)
        self.embed = nn.Linear(resnet.fc.in_features, embed_size)
        '''
        resnet = models.resnet152(pretrained=True)
        modules = list(resnet.children())[:-1]      # delete the last fc layer.
        self.resnet = nn.Sequential(*modules)
        self.linear = nn.Linear(resnet.fc.in_features, embed_size)
        self.bn = nn.BatchNorm1d(embed_size, momentum=0.01)

    def forward(self, images):
        '''
        features = self.resnet(images)
        features = features.view(features.size(0), -1)
        features = self.embed(features)
        '''
        with torch.no_grad():
            features = self.resnet(images)
        features = features.reshape(features.size(0), -1)
        features = self.bn(self.linear(features))
        return features
    

class DecoderRNN(nn.Module):
    def __init__(self, embed_size, hidden_size, vocab_size, num_layers=1):
        super(DecoderRNN, self).__init__()
        
        self.embed_size = embed_size
        self.hidden_size= hidden_size
        self.vocab_size = vocab_size
        self.num_layers = num_layers
        self.embed = nn.Embedding(vocab_size, embed_size)
        self.lstm = nn.LSTM(embed_size, hidden_size, num_layers)
        self.linear = nn.Linear(hidden_size, vocab_size)
        #self.init_weights()
    '''
    def init_weights(self):
        """Initialize weights."""
        self.word_embeddings.weight.data.uniform_(-0.1, 0.1)
        self.linear.weight.data.uniform_(-0.1, 0.1)
        self.linear.bias.data.fill_(0)
    '''
    def forward(self, features, captions):
        embeddings = self.embed(captions)
        embeddings = torch.cat((features.unsqueeze(1), embeddings), 1)
        packed = pack_padded_sequence(embeddings, lengths, batch_first=True) 
        hiddens, _ = self.lstm(packed)
        outputs = self.linear(hiddens[0])
        return output

    def sample(self, inputs, states=None, max_len=20):
        " accepts pre-processed image tensor (inputs) and returns predicted sentence (list of tensor ids of length max_len) "
        
        sampled_ids = []
        inputs = inputs.unsqueeze(1)
        
        for i in range(max_len):
            hiddens, states = self.lstm(inputs, states)          # hiddens: (batch_size, 1, hidden_size)
            outputs = self.linear(hiddens.squeeze(1))            # outputs:  (batch_size, vocab_size)
            _, predicted = outputs.max(1)                        # predicted: (batch_size)
            sampled_ids.append(predicted)
            inputs = self.embed(predicted)                       # inputs: (batch_size, embed_size)
            inputs = inputs.unsqueeze(1)                         # inputs: (batch_size, 1, embed_size)
        sampled_ids = torch.stack(sampled_ids, 1)                # sampled_ids: (batch_size, max_seq_length)
        
        return sampled_ids