unsupervised_captioning

unsupervised_captioning copied to clipboard

Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.13.1 to 2.7.2. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.7.2 Release 2.7.2 This releases introduces several vulnerability fixes: Fixes a code injection in saved_model_cli (CVE-2022-29216) Fixes...

dependabot[bot]

Description link is disabled

2

We need to Google Drive or Onedrive link for the file generated (description). I couldn't access to baidunet disk system.

greeksharifa

Hey yang, I encountered the below mentioned error when I ran "python preprocessing/extract_descriptions.py" command. Can you resolve this issue. Thank you in advance Traceback (most recent call last): File "preprocessing/extract_descriptions.py",...

Anirudh-crypto

Dear Yang, I encounter some problems when running your code. First, the Dataset you given in the first step is out of date. And also the Baidu Cloud link you...

ShawnRBT

error

15

from config import TF_MODELS_PATH ImportError: cannot import name 'TF_MODELS_PATH' from 'config' (D:\python3.7\lib\site-packages\config\__init__.py) what's the mean of TF_MODELS_PATH? I can't find it in config,should I create it by myself? @fengyang0317 can...

feng-yun-anhui

eval_all.py

1

https://github.com/fengyang0317/unsupervised_captioning/blob/0e75b6aff4cc9e94249bc272fc5490e566ef5d7c/eval_all.py#L4 https://github.com/fengyang0317/unsupervised_captioning/blob/0e75b6aff4cc9e94249bc272fc5490e566ef5d7c/eval_all.py#L92 https://github.com/fengyang0317/unsupervised_captioning/blob/0e75b6aff4cc9e94249bc272fc5490e566ef5d7c/eval_all.py#L93 multiprocessing.pool.MaybeEncodingError: Error sending result: 'NotFoundError()'. Reason: 'PicklingError("Can't pickle : attribute lookup __builtin__.module failed",)' is this result happen because of the module multiprocessing?Have you had this problem?

ironmanx1

about the reproduce of metrics reported in paper?

39

Hi Yang, I am reproducing the experiments in the paper. Can you give some hints of the best combination of hyper-parameters? Such as batch_size, learning_rate, and how many steps is...

hugddygff

Hi, yang, May I ask you a question?

2

If I want to use tensorflow v2.0 to run the code? what should I do? There's no tf.contrib. I tried to use tf.compat.v1, but it doesn't work. It seems that...

fresh382227905

question about the training process

4

Hi Yang: I use the code that you release in the github, and I run the train code with the parameter: two GPUs, batch_size 256, lr_rate 0.0005, now training 26000...

sakura2233565548

我使用您在百度网盘中提供的数据，当运行im_caption_full.py时出现如下错误： Traceback (most recent call last): File "/home/wangtao/miniconda3/envs/tensorflower1.4.0-py3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call return fn(*args) File "/home/wangtao/miniconda3/envs/tensorflower1.4.0-py3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1341, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/home/wangtao/miniconda3/envs/tensorflower1.4.0-py3.6/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1429, in...

ttx213