search

mczhuge / Kaleido-BERT

💐Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
MIT License
263 stars 19 forks source link

The problem about the third step:Download Dependancy #1

Closed tangyuhao2016 closed 3 years ago

tangyuhao2016 commented 3 years ago

Thank you for sharing such great work.

When I run the sh get_checkpoint.sh, I get the mistake like below:

Resolving icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com (icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com)... 47.92.17.218 Connecting to icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com (icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com)|47.92.17.218|:80... connected. HTTP request sent, awaiting response... 403 Forbidden.

And when I click the link directly, I get the mistake like below:

This XML file does not appear to have any style information associated with it. The document tree is shown below.

AccessDenied You have no right to access this object because of bucket acl. 607C319BB6DA383338EC6AFD icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com

May you provide the solution?

mczhuge commented 3 years ago

Hi, Yuhao, Thank you for informing this error, I feel sorry about this mistake. I have repaired the shell file get_checkpoint.sh, please modified it according to https://github.com/mczhuge/Kaleido-BERT/blob/main/scripts/checkpoint/get_checkpoint.sh and try it again. Best regards.

tangyuhao2016 commented 3 years ago

Thank you for your help, the problem has been solved. However, the download speed is so slow, I have tried several times and different networks are used. It's only tens of K per second, and it's very easy to interrupt. Could you upload the source data to the Baidu cloud disk or Google cloud disk?

mczhuge commented 3 years ago

Since the limits of authority, we cannot directly put these data in Baidu or Google disk right now. But there may have two solutions:

1) First, you can download these datasets by Xunlei or some other similar tools. I just copy the links to Xunlei, such as http://icbu-ensa-sc.oss-cn-zhangjiakou.aliyuncs.com/mingchen.zgmc/KaleidoBERT_TF_CODE/datasets/checkpoint/kaleidobert.ckpt-50683.data-00000-of-00001, and the download speed can achieve 10MB/s. 2) Waiting for Alibaba Disk ^_^

I wish it could be helpful for you.

tangyuhao2016 commented 3 years ago

Thank you for your help. Even though I use Xunlei with the vip, the speed is only 200-300k/s. And the FashionGen dataset is very large, one download link is about 16.5g and there are several links.

mczhuge commented 3 years ago

Yes. The pre-processed datasets are large. I did not use the Xunlei VIP but also get a 7MB/s download speed. Can you add my WeChat? ID: tjpxiaoming