image-captioning
image-captioning copied to clipboard
JDAI-CV
Implementation of 'X-Linear Attention Networks for Image Captioning' [CVPR 2020]
你好，请问可以提供ensemble的代码吗，还有论文说的以senet154为backbone是指将faster rcnn的backbone换成了senet 还是直接用它提取特征？有提取好的特征数据吗？
How to generate the coco_train_input.pkl and coco_train_target.pkl?
How to generate the visualization of attended image regions along the caption generation processes.
I have a question for how to generate the visualization of attended image regions along the caption generation processes. Would you mind releasing some codes?
Thank you very much for making the code open source I can find 4 configs about xlan and transformer in the experiment folder Can you provide the basic model(updown) of...
1) I used the provided caption_model_47.pth from xlan experiment and the following commands to do the test. However, **all test metrics are 0 when I used the def decode_beam which...
The model I'm training is fed with global region feature of each image, it doesn't use local feature based on regions. Do you think I can apply your technique to...
Hi! Thanks for the written paper and the availabe code. I have what may be a stupid question, but I didn't find a straight answer to it anywhere: When evaluating...
[INFO: 2024-03-16 05:55:12,296] ######## Epoch (VAL)2 ######## [INFO: 2024-03-16 05:55:12,296] {'Bleu_1': 0.10388235294117525, 'Bleu_2': 0.015665952215665777, 'Bleu_3': 0.0023566989464306317, 'Bleu_4': 1.1693743696593336e-07, 'METEOR': 0.06880237033174463, 'ROUGE_L': 0.10528904602185862, 'C IDEr': 0.05029230331138939, 'SPICE': 0.04714478772067636} [INFO: 2024-03-16 06:00:21,652]...
