sightseq

sightseq copied to clipboard

能提供新的依赖版本么？

5

liuzhuang1024

How is the picture processed in sequence_generate?

1

The shape of the picture is (Batch, Channel, H, W) The data shape that the sequence_generate can receive is (batch, seq_len,...) I did not find a solution in your code,...

xiaoxiaokuye

Not found recurrent layer in model files

1

I checked the network roughly, and I found it seems no recurrent layers like Bi-LSTM？ Is this repo another implementation for CRNN? I just see several CNN backbone and fully...

courao

The vanilla cnn downsampling architecture cannot recover spatial information of a image

1

The convolutional part of the architecture act as a encoder part, it capture image's contexture information, the architecture should ensemble a decoder part (deconvolution layer or RNN layer) to recover...

zhiqwang