TimeSformer video train, deprecated pixel format used, make sure you did set range correctly (repeated 10 more times)

[chennankuan]

[09/13 10:16:51] epoch:[ 1/15 ] train step:60 loss: 0.38537 lr: 0.000625 top1: 1.00000 top5: 1.00000 batch_cost: 0.25389 sec, reader_cost: 0.00016 sec, ips: 3.93872 instance/sec. deprecated pixel format used, make sure you did set range correctly (repeated 13 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 8 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 6 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 13 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 13 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 13 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 11 more times) deprecated pixel format used, make sure you did set range correctly deprecated pixel format used, make sure you did set range correctly (repeated 12 more times) 训练timesformer video 分类模型，提示这个问题，不知道说明原因引起的

[jerrywgz]

您好，请问问题还是否需要解决，目前多模态视频能力集成在PaddleMIX中，https://github.com/PaddlePaddle/PaddleMIX/tree/develop 可以在这个repo下提出您的需求