Training results

The model can be trained using the following command:

python Video_seq2seq.py process_main --path_prj '/media/santanu/9eb9b6dc-b380-486e-b4fd-c424a325b976/Video Captioning/' --caption_file video_corpus.csv --feat_dir features --cnn_feat_dim 4096 --h_dim 512 --batch_size 32 --lstm_steps 80 --video_steps=80 --out_steps 20 --learning_rate 1e-4--epochs=100

Parameter	Value
Optimizer	Adam
learning rate	1e-4
Batch size	32
Epochs	100
cnn_feat_dim	4096
lstm_steps	80
out_steps	20
h_dim	512

The output log of the training is as follows:

Batch starting index: 1728 Epoch: 99 loss: 17.723186 Elapsed time: 0.21822428703308105
Batch starting index: 1760 Epoch: 99 loss: 19.556421 Elapsed time: 0.2106935977935791
Batch starting index: 1792 Epoch: 99 loss: 21.919321 Elapsed time: 0.2206578254699707
Batch starting index: 1824 Epoch: 99 loss...