X-Decoder
X-Decoder copied to clipboard
microsoft
Official Implementation of X-Decoder for generalized decoding for pixel, image and language
**I encountered a simple bug when evaluating. How can this problem be solved? It seems like 817920 is three times as much as 272540. ** ``` /home/user/anaconda3/envs/xdecoder/lib/python3.9/site-packages/detectron2/structures/image_list.py:88: UserWarning: __floordiv__ is...
Thanks for your work！ I notice the code in "demo_captioning.py ": `if 'novg' not in pretrained_pth: assert False, "Using the ckpt without visual genome training data will be much better."`...
The [HF Spaces demo](https://huggingface.co/spaces/xdecoder/Demo) keeps building for a long time and shows no sight of progress. The [Instruct X decoder demo](https://huggingface.co/spaces/xdecoder/Instruct-X-Decoder) is similarly not working, as I get a stack...
Please accept this contribution adding the standard Microsoft SECURITY.MD :lock: file to help the community understand the security policy and how to safely report security issues. GitHub uses the presence...
![microsoft-github-policy-service[bot] avatar](https://avatars.githubusercontent.com/in/95686?v=4 "microsoft-github-policy-service[bot] avatar"){kind=avatar}
Bumps [transformers](https://github.com/huggingface/transformers) from 4.19.2 to 4.30.0. Release notes Sourced from transformers's releases. v4.30.0: 100k, Agents improvements, Safetensors core dependency, Swiftformer, Autoformer, MobileViTv2, timm-as-a-backbone 100k Transformers has just reached 100k stars...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [gradio](https://github.com/gradio-app/gradio) from 3.13.0 to 3.34.0. Release notes Sourced from gradio's releases. v3.34.0 No release notes provided. v3.33.1 No release notes provided. v3.33.0 No release notes provided. v3.32.0 No release...
I can only find the coco 2014 karpathy splits. Where and how to get the coco_caption_karpathy_val2017.arrow?
Following the commands [here](https://github.com/microsoft/X-Decoder/tree/seginw?tab=readme-ov-file#download) I get 409. ```bash (x-decoder) ➜ X-Decoder git:(seginw) sh install_cococapeval.sh --2024-07-13 22:53:13-- https://projects4jw.blob.core.windows.net/x-decoder/release/coco_caption.zip Resolving projects4jw.blob.core.windows.net (projects4jw.blob.core.windows.net)... 20.150.87.132 Connecting to projects4jw.blob.core.windows.net (projects4jw.blob.core.windows.net)|20.150.87.132|:443... connected. HTTP request sent, awaiting...
Attribute 'arrows' does not exist in the metadata of dataset 'vlp_captioning_val': metadata is empty. File "xxx/datasets/dataset_mappers/vlp_dataset_mapper.py", line 94, in __init__ self.all_arrows = MetadataCatalog.get(dataset_name).arrows
Hello! I have observed that the code of SEEM and X-deocder exhibit numerous common elements. Could you please summarize the dissimilarities and similarities between them?
