meshed-memory-transformer icon indicating copy to clipboard operation
meshed-memory-transformer copied to clipboard

Meshed-Memory Transformer for Image Captioning. CVPR 2020

Results 57 meshed-memory-transformer issues
Sort by recently updated
recently updated
newest added

How much memory is needed, 16g memory seems not enough?

When running to epoch 3 to calculate ROUGE is the program aborted?

Hello, author, thank you very much for the open code. I have a small request: Can I know the specific configuration of the code you are running (such as GPU,...

Traceback (most recent call last): File "/mnt/Pycharm_Remote/DLCT_test/train.py", line 335, in scores = evaluate_metrics(model, dict_dataloader_val, text_field) File "/mnt/Pycharm_Remote/DLCT_test/train.py", line 61, in evaluate_metrics **{'boxes': boxes, 'grids': grids, 'masks': masks}) File "/mnt/Pycharm_Remote/DLCT_test/models/captioning_model.py", line...

There are six files in the Annotations folder. How to set the '--annotation_folder' parameter? Also does '--features_path' refer to the coco_detections.hdf5 file ![image](https://user-images.githubusercontent.com/51855588/138074268-007de0fe-6298-42b5-9e85-dd45a9d9a73f.png)

Hello. Thanks for sharing your code. I checked `coco_detections.hdf5` file using HDFView. I understand that `imgid_features` and `imgid_boxes` are extracted from Faster R-CNN(with ResNet101). But, I was wondering how you...

Hi, Can captions be generated for new images out from the coco dataset? Say for example, i want to generate caption on my profile pic, is it possible with this...

Thanks for sharing your code with us. But can you share me the code to generate the captions of images like the figure 3/4 in your artical ? I want...

Do you have the issue about downloading coco_detections.hdf5? Recently, I met the issue. It showed that too many people were downloading it from the google driver and let me try...

It trains well in XE part until it Switch to RL. Does it because of the lack of my graphics card memory? Anyone met this problem before? Please tell me...