search

xiadingZ / video-caption.pytorch

pytorch implementation of video captioning
MIT License
401 stars 130 forks source link

S2VTAttModel doesn't converge #9

Closed dmandreev closed 6 years ago

dmandreev commented 6 years ago

Hello DingXia! I'm trying to repro your results and train S2VTAttModel with train data you linked in read.me with train.py params --gpu 0,1,2,3 --epochs 9001 --batch_size 450 --checkpoint_path data/save --feats_dir data/feats/resnet152/train-video --dim_vid 2048 --model S2VTAttModel But after 4 days of training, train/loss still too high. iter 12 (epoch 5463), train_loss = 23.042719 Does I'm doing something wrong?

xiadingZ commented 6 years ago

It's normal, my model also has this train_loss. you can test it to see blue/cider... score