Jenna comments

Results 6 comments of


                                            Jenna

error in dcnv3_im2col_cuda: no kernel image is available for execution on the device

> I met the same error as I installed DCNv3 in conda env via whl file. Do you solve it ? If so, let me know. I kept getting errors...

Can not export detection model to onnx

Did you solve that issue?

Classification training on custom dataset

Did you train with pretrained model? Did anyone succeed in fine-tuning?

[bug] how to train fine-tuning classification model (size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([4]).)

how to convert Nc1..? --- ---

[bug] how to train fine-tuning classification model (size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([4]).)

I tried changing the file configuration in the following order. I'm training, but the data is big, so I'll let you know the results in the future 1. download pth...

[bug] how to train fine-tuning classification model (size mismatch for head.bias: copying a param with shape torch.Size([1000]) from checkpoint, the shape in current model is torch.Size([4]).)

[bug] I don't think there's progress in training.. Everything's the same as loss May I know the reason?