WEI

dpccn这个模型，max_seq_length不能是任意数。 不然经过self._block(x)这个模块后，得到的形状不是[batch_size, filter_num]，而是[batch_size, filter_num, 2] max_seq_length设置成，减2后，不断除2，得到的结果是1不是2，就行。

> Hi, [here](https://github.com/DavidHuji/CapDec#datasets) are the instructions. Please let me know if you encounter any issue. Hi, I had the same problem, I didn't get single_caption_per_sample_val.json, and what does it mean...

I gave up, I found other code on GitHub and then conducted an evaluation, referring to https://github.com/jmhessel/clipscore. Simply save the generated descriptions and label descriptions into two lists, refer to...

Hello, have you solved this problem? I also encountered this problem, in the graph I generated, I represented the image points in red and the caption points in blue, I...

> Hello, have you solved this problem? I also encountered this problem, in the graph I generated, I represented the image points in red and the caption points in blue,...