Iasonas Christoulakis comments

Repositories
Issues
Comments

Results 2 comments of


                                            Iasonas Christoulakis

Fine-tuning CLIP for image object detection.

could you share the way you implement the clip image_encoder as backbone?

Expected tensor for argument #1 'input' to have the same type as tensor for argument #2 'rois'; but type torch.cuda.HalfTensor does not equal torch.cuda.FloatTensor

same problem but fixed with command `.float()`. This error referred to the `tensor.dtype` such as `torch.float16` is the half tensor of `tensor.float32`!