rangoliu

@sid027 I changed the num_output of "cls_score" layer to 201 and the num_output of "bboxes_pred" layer to 804 in train.prototxt. And I trained it on imagenet dataset.

@sid027 because there are 200 classes in imagenet dataset ，and 201 classes with “background” ，804 = 201 \* 4 are bounding boxes

because a bounding box is [xmin,ymin,xmax,ymax]，there are four numbers for a box. [xmin,ymin] is the left-top pixel location of this box in original image ,and [xmax,ymax] is the right-bottom.

@sid027 you needn't to put each class in a subfolder because images will be shuffled before training,and background will be generated automatically.

see this https://github.com/bgshih/crnn/issues/1 @rremani

agree with @RubenS02

@yuleiqin I meet the same problem, have you solved this?

Check the weights of temporal_attention/temporal_attention.ckpt. This ckpt contains unet weights, so whatever your custom model is loaded, unet weights will be reloaded when you load this ckpt.

> > Check the weights of temporal_attention/temporal_attention.ckpt. This ckpt contains unet weights, so whatever your custom model is loaded, unet weights will be reloaded when you load this ckpt. >...

Hi, It seems like the address of facenet.pth is changed, which is https://huggingface.co/lllyasviel/Annotators/blob/main/facenet.pth. Please check your controlnet_aux version. We use controlnet-aux==0.0.3 in PowerPaint.