densecap

densecap copied to clipboard

  I am having trouble with the above error.

japanese-university-student

Your README say that requirement is Python3.6 , but coco-caption is inside of python2 requirement, could you release the python3 version of coco-caption? 

BruceChen15

Thank for your work!! How can I inference for an image?

Tien-203

Question about the `recall` and `recall area`

2

I tried the code in this repo and got the result `proposal recall area 41.133031`, which is much lower than the `Average Recall` value (52.95, from Tab. 4) shown in...

textcunma

RuntimeError Traceback (most recent call last) in () 1 if __name__ == "__main__": ----> 2 main(args) 5 frames in main(args) 69 70 epoch_loss = train(train_epoch, model, optimizer, train_loader, ---> 71...

lokeaichirou

Run the test. py

3

Error: （1）D:\Anaconda2\envs\py36\python.exe D:/PythonCode1/densecap-master/test.py --cfgs_file cfgs/anet.yml --densecap_eval_file ./tools/densevid_eval/evaluate.py --batch_size 1 --start_from ./checkpoint/anet-2L-e2e-mask/model_epoch_19.t7 --id anet-2L-e2e-mask-19 --val_data_folder validation --learn_mask --gated_mask --cuda D:/PythonCode1/densecap-master/test.py:82: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader...

niu1970

Snyk has created this PR to fix one or more vulnerable packages in the `pip` dependencies of this project. #### Changes included in this PR - Changes to the following...

meghasfdc

When testing I get this error, how can I fix this?

3

Namespace(attn_dropout=0.2, batch_size=1, cap_dropout=0.2, cfgs_file='cfgs/yc2.yml', cuda=True, d_hidden=2048, d_model=1024, dataset='yc2', dataset_file='./data/yc2/yc2_annotations_trainval.json', densecap_eval_file='./tools/densevid_eval/evaluate.py', densecap_references=['./data/yc2/val_yc2.json'], dur_file='./data/yc2/yc2_duration_frame.csv', feature_root='/checkpoint/luoweizhou/old_checkpoint02/dat/yc2/rgb_motion_1d', gated_mask=False, id='yc2-2L-gt-mask-19', image_feat_size=3072, in_emb_dropout=0.1, kernel_list=[1, 3, 5, 7, 9, 11, 15, 21, 27, 33, 41, 49, 57,...

abhranil08

Hello, I have a question about training cap_model with end-to-end maksed transformer. In the code, the cap_model is trained with "window_mask = (gate_scores * pred_bin_window_mask.view(B, T, 1)". As I understand,...

Naren00

Use your pre-training model and code

1

Hello!Since I am new to this direction, I would like to trouble you to write a complete use process for your project, that is, how to use your pre-training model...

niu1970