search

mrlooi / rotated_maskrcnn

Rotated Mask R-CNN: From Bounding Boxes to Rotated Bounding Boxes
MIT License
347 stars 62 forks source link

PPC pretrained weights #20

Open trungpham2606 opened 4 years ago

trungpham2606 commented 4 years ago

❓ Questions and Help

@mrlooi Can you public your pretrained weights on PPC dataset ?

mrlooi commented 4 years ago

Hey unfortunately I don't have the pretrained weights with me. In any case the MSCOCO pretrained weights should be more better - it's more general

trungpham2606 commented 4 years ago

@mrlooi In addition, You have not published your paper yet, have you ?

mrlooi commented 4 years ago

Nope, it takes work, and doubt it's going to make much of an impact anyway. I'm not a full time researcher, so publications and citations are not as important to me xD

trungpham2606 commented 4 years ago

@mrlooi I often meet this error after some training iterations: image Can you tell me how to solve this issue ?

mrlooi commented 4 years ago

It would seem that the input batch size is empty (0 x 1 x ...). A good way to check is backtrack where the input became empty. I haven't seen this issue before, but if you do find out the cause, please let me know

trungpham2606 commented 4 years ago

@mrlooi Yeah sure, Iam training with my own dataset to see if this error still occurs.

trungpham2606 commented 4 years ago

@mrlooi I think the error comes from the model not about the dataset. For PPC dataset, i had printed out the images when the errors come out. image image

The error comes with different images each times. The objects inside the images I guess they're not too small. Do you have any ideas about this ?

mrlooi commented 4 years ago

Hey good question. I think it could be that the ground truth rotated bboxes for those objects did not have good IoU fit with any of the rotated anchors

trungpham2606 commented 4 years ago

@mrlooi I had changed some threshold for being able to train PPC dataset. Thank you for your prompt support!

trungpham2606 commented 4 years ago

@mrlooi Excuse me but can you please give me some sources of reference you had used in your work ? Does RRPN you used come from this paper: Arbitrary-Oriented Scene Text Detection via Rotation Proposals ?(https://arxiv.org/pdf/1703.01086.pdf)

mrlooi commented 4 years ago

Yes RRPN and MaskRCNN are the main ones

elepherai commented 3 years ago

@mrlooi I had changed some threshold for being able to train PPC dataset. Thank you for your prompt support!

@trungpham2606 Hi, could you tell me what thresholds did you change for training PPC dataset? Thanks~