Inferring shape via flatten operator

4

Hum, I’m afraid you can’t calculate that in __init__ without prior knowledge of the input shape.
You could imagine passing an input shape as argument to the __init__. In this situation, you can infer the shape by performing a forward pass over the convolutional blocks. Something like

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable

class Net(nn.Module):
    def __init__(self, input_shape=(1, 28, 28)):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()

        n_size = self._get_conv_output(input_shape)
        
        self.fc1 = nn.Linear(n_size, 50)
        self.fc2 = nn.Linear(50, 10)

    # generate input sample and forward to get shape
    def _get_conv_output(self, shape):
        bs = 1
        input = Variable(torch.rand(bs, *shape))
        output_feat = self._forward_features(input)
        n_size = output_feat.data.view(bs, -1).size(1)
        return n_size

    def _forward_features(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        return x

    def forward(self, x):
        x = self._forward_features(x)
        x = x.view(x.size(0), -1)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = F.relu(self.fc2(x))
        return F.log_softmax(x)
9 Likes