long action sequence

[liloewe]

Hello, author, how to generate a long action sequence?

[exitudio]

Hi, We have created sample codes and visualizations in the edit.ipynb notebook. Please refer to the 'Long Range' section in edit.ipynb. The model requires a list of text and the number of frames for each text.

text = ['a person walks forward then turn left.',
      'a person crawling from left to right',
      'a person dribbles a basketball then shoots it.',
      'the person is walking in a counter counterclockwise circle.',
      'a person is sitting in a chair, wobbles side to side, stands up, and then start walking.']
m_length = torch.tensor([192, 196,  84, 164, 196])
pred_pose = mmm.long_range(text, m_length.cuda(), output='concat')

[liloewe]

您好，我们在 中创建了示例代码和可视化效果。请参阅 中的“长距离”部分。该模型需要一个文本列表和每个文本的帧数。edit.ipynb notebook``edit.ipynb

text = ['a person walks forward then turn left.',
      'a person crawling from left to right',
      'a person dribbles a basketball then shoots it.',
      'the person is walking in a counter counterclockwise circle.',
      'a person is sitting in a chair, wobbles side to side, stands up, and then start walking.']
m_length = torch.tensor([192, 196,  84, 164, 196])
pred_pose = mmm.long_range(text, m_length.cuda(), output='concat')

Thank you. It worked very well