search

z-x-yang / Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
GNU Affero General Public License v3.0
2.77k stars 334 forks source link

运行分割第一帧之后下载的是什么，下的很慢 #86

Open CongSuxu opened 1 year ago

CongSuxu commented 1 year ago

I NMT{PJ X{PSN@~)K205}V 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。

The-Martyr commented 10 months ago

I NMT{PJ X{PSN@~)K205}V 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。

请问解决了吗

CongSuxu commented 10 months ago

解决了，第一次运行需要下载这个，等他下载完就好了，后面运行就很快了

------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:41 PM @.>; @.**@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86)

如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。

请问解决了吗

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

The-Martyr commented 10 months ago

解决了，第一次运行需要下载这个，等他下载完就好了，后面运行就很快了 … ------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:41 PM @.>; @.**@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86) 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。 请问解决了吗 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

是的，之前也是这样，但今天使用时突然出现了其他的问题如下 capture_20231102224626439

CongSuxu commented 10 months ago

我可能解决不了，我不是做这个方向研究的，只是用一下这个技术。

------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:49 PM @.>; @.**@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86)

解决了，第一次运行需要下载这个，等他下载完就好了，后面运行就很快了 … ------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:41 PM @.>; @.@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86) 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。 请问解决了吗 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

是的，之前也是这样，但今天使用时突然出现了其他的问题如下

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

yamy-cheng commented 10 months ago

I NMT{PJ X{PSN@~)K205}V 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。

The model weights of Grounding-DINO will be downloaded when using SAM-Track for the first time. In general, the weight will be saved in ~/.cache/.

The-Martyr commented 10 months ago

I NMT{PJ X{PSN@~)K205}V 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。

The model weights of Grounding-DINO will be downloaded when using SAM-Track for the first time. In general, the weight will be saved in ~/.cache/.

Thank you very much!😊

The-Martyr commented 10 months ago

我可能解决不了，我不是做这个方向研究的，只是用一下这个技术。 … ------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:49 PM @.>; @.**@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86) 解决了，第一次运行需要下载这个，等他下载完就好了，后面运行就很快了 … ------------------ Original ------------------ From: "z-x-yang/Segment-and-Track-Anything" @.>; Date: Thu, Nov 2, 2023 10:41 PM @.>; @.@.>; Subject: Re: [z-x-yang/Segment-and-Track-Anything] 运行分割第一帧之后下载的是什么，下的很慢 (Issue #86) 如图，请问这个safetensors是什么，我想手动下载一下，可以的话请顺便告知放在哪里。 请问解决了吗 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.> 是的，之前也是这样，但今天使用时突然出现了其他的问题如下 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.>

只需要将huggingface的bert-base-uncased仓库的对应文件下载到~/.cache/huggingface/transformers/bert-base-uncased文件夹中，再将get_tokenizer.py中加载的tokenizer和model改为绝对路径就可以了。