Alee Yang

Is there a way to change the ‘Starting pose codes’？

1

Hi，thank you for your work again! It really inspires me and bring me interest in deep learning! amazing job! Problem： I found the generated music dance videos in the same...

error in running code in caisa-b

9

I use this command `python3 gaitgraph_casia_b.py fit --config configs/casia_b.yaml` but it always give me error reply ``` File "gaitgraph_casia_b.py", line 77, in validation_step y_hat = self(x) File "/home/fuyang/anaconda3/envs/gaitgraph/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110,...

Cannt download the BEATs_iter3+ (AS2M) (cpt2)

10

This XML file does not appear to have any style information associated with it. The document tree is shown below. AuthenticationFailed Server failed to authenticate the request. Make sure the...

### What is the feature? 我现在有多个视频，需要预测得到133关键，我参考demo使用rtmdet+rtmpose-l ，一张图像在V100推理需要1s（单张图），如何实现多图同时进行inference（放在batch 维度） ### Any other context? 或者有其他提高推理速度的方法吗 _No response_

请问， 在shareGPT4V论文(https://arxiv.org/pdf/2311.12793) Figure 3中的Unified Prompt 具体指的是什么？论文中没有给出具体的描述

what a great job in ICCV23! I have one question about the experiment on Image retrieval. The BOT ReId model you used inputs RGB images, which have three channels. However,...

你好，有多节点多卡运行代码的脚本吗

你好，作者， ShortSideScale(size=short_size), CenterCropVideo(crop_size=crop_size), 这个是为了适配后面的模型输入来计算特征纬度的相似度吗，还是为了减少计算量呢？ 如果是为了减少计算量，这两个transform是不是可以去掉？ https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/294993ca78bf65dec1c3b6fb25541432c545eda9/opensora/eval/eval_common_metric.py#L131