lokvke

how can i get ROI from nvcv.ImageBatchVarShape

4

how can i get ROI from nvcv.ImageBatchVarShape, like: x_roi = x[y1:x1, y1+height, x1 + width], or x[y1:x1, y1+height, x1 + width] = x_roi...

Does the May's pretrained model support chinese audio?

6

hi there, i have a question as the tile says "does the May's pretrained model support chinese audio?", i tried to use May's pretrained model and a chinese audio file,...

IndexError: index 676 is out of bounds for dimension 0 with size 676

7

| load 'model' from 'checkpoints/audio2motion_vae/model_ckpt_steps_400000.ckpt', strict=True | WARN: checkpoints/motion2video_nerf/may_torso/lm3d_radnerf_torso.yaml not exist. | load 'model' from 'checkpoints/motion2video_nerf/may_torso/model_ckpt_steps_250000.ckpt', strict=True trainval: Smooth head trajectory (rotation and translation) with a window size of 7...

geneface++比geneface难训练，每次训练的模型都不满意

only render with the head model, torso part shows

2

When i render just with the head model, some torso part edge also be rendered as the picture shows. This also happen with the provided may_head model. 

推理的时候可以把batch_size设置高一点吗？

不同图像尺寸对rtmp推流速度的影响

1

发现当图像尺寸太大的话，推流到rtmp的速度会比较慢，这部分可以优化吗？

how to use my own dataset?

4

how can i user my own dataset 'train.csv' and 'test.csv' like kaggle format?