stillbetter
stillbetter
Hi, neka-nat, Have you complete the testing part? Badly need your test code
You need to make sure the dataset in the right directory. ---Original--- From: "WANG Gefei" Date: Sun, Jun 2, 2019 22:48 PM To: "dyelax/Adversarial_Video_Generation"; Cc: "Subscribed"; Subject: Re: [dyelax/Adversarial_Video_Generation] Error...
好的，谢谢，请问如果代码中调用了numpy scipy这种的也会一并打包进so库么？
Another question is, since we can get the `pred_original_sample` in every step in pipeline, why we not take it directly, instead keep the denoising step by step. This may be...
Greatly thanks for your reply! Exciting to cry~ 1. So can I just treat `v_prediction` as the prediction object is a denoised latents, and `epsilon` as the object is noise?...
Well, let me make Quest.2 clear. Why the a same `v_prediction` corresponding to two inverted formulars, in train and step func.
> I am using the Qwen2-VL-2B model for a classification task, and I want to modify the Qwen2VLForConditionalGeneration by adding a linear classification head to adapt it to the task....
> > 你好，非常感谢分享代码。我遇到这样一个问题，我自己生成了12阶贝塞尔锚点的json文件，并且在修改order变量，num_regression_parameters=26之后开始训练，但是代码报错在cubic_bezier_curve_segment中，报错如下 > > ``` > > pytorch-auto-drive/utils/curve_utils.py", line 254, in cubic_bezier_curve_segment > > res = transform_matrix.matmul(control_points.permute(0, 2, 1).unsqueeze(-1)) # B x 2 x 4 x 1 > >...
> You can try to convert the lightning lora weight file using the following script, and then use the load_lora function to load the converted weights and set alpha to...