VSUA-Captioning
VSUA-Captioning copied to clipboard
ltguo19
Code for "Aligning Linguistic Words and Visual Semantic Units for Image Captioning", ACM MM 2019
Thanks a lot! How can I solve AttributeError: module 'misc.utils' has no attribute 'pickle_dump'
Thanks a lot! How can I get the file, coco-train-idxs.p?
When I default parameter: _python train.py --gpus 0 --id experiment-xe --geometry_relation True_ , it can run but in 6 epoch around errors occur as follows: I guess that 1. I...
An error was encountered while evaluating the SPICE score，the detial as follow:  I set the pycocoevalcap file followed as README. I want to know how to fix it. I...
Traceback (most recent call last): File "train.py", line 155, in train(opt) File "train.py", line 76, in train data = loader.get_batch('train') File "VSUA-Captioning-master/dataloader.py", line 144, in get_batch ix, tmp_wrapped = self._prefetch_process[split].get()...
Traceback (most recent call last): File "train.py", line 171, in train(opt) File "train.py", line 102, in train reward = get_self_critical_reward(decoder, core_args, vrg_data, fc_feats, att_feats, weak_relas, att_masks, data, gen_result, opt) File...
Can't download the files `coco_img_sg.zip` and `coco_pred_sg_rela.npy` from this [link](https://drive.google.com/drive/folders/1GvwpchUnfqUjvlpWTYbmEvhvkJTIWWRb?usp=sharing) Can't download the files `vsua_box_info.pkl` from this [link](https://drive.google.com/open?id=1G9_ZdjyIprl2wyWCExslWTWOimJf3x8G) Could you provide another link? Thank U
def forward(self, obj_vecs, attr_vecs, rela_vecs, edges, rela_masks=None): # for easily indexing the subject and object of each relation in the tensors obj_vecs, attr_vecs, rela_vecs, edges, ori_shape = self.feat_3d_to_2d(obj_vecs, attr_vecs, rela_vecs,...
`coco_pred_sg_rela.npy` contains the vocabularies for the object, attribute and relation labels. While it has keys `dict_keys(['i2w', 'rela_dict', 'w2i'])`, i2w-->object w2i-->attribute rela_dict-->relation Is it right? And the three dicts all include...
