Crnn how to obtain a gradcam for characters

Zrufy · November 22, 2022, 9:05am

Hi all, I’ve been looking for a solution to this problem for some time.
I have a crnn from which I would like to get a heatmap to see and see where there is more concentration and see which characters it focuses on and more.
But after so many attempts I still haven’t been able to get the result I was looking for.
Could anyone help me?

github.com

meijieru/crnn.pytorch/blob/master/models/crnn.py

import torch.nn as nn


class BidirectionalLSTM(nn.Module):

    def __init__(self, nIn, nHidden, nOut):
        super(BidirectionalLSTM, self).__init__()

        self.rnn = nn.LSTM(nIn, nHidden, bidirectional=True)
        self.embedding = nn.Linear(nHidden * 2, nOut)

    def forward(self, input):
        recurrent, _ = self.rnn(input)
        T, b, h = recurrent.size()
        t_rec = recurrent.view(T * b, h)

        output = self.embedding(t_rec)  # [T * b, nOut]
        output = output.view(T, b, -1)

        return output

This file has been truncated. show original

This is the project I’m referring to