EfficientDet.Pytorch

EfficientDet.Pytorch copied to clipboard

https://app.circleci.com/jobs/github/toandaominh1997/EfficientDet.Pytorch/58 https://github.com/toandaominh1997/EfficientDet.Pytorch/blob/master/utils/vis_bbox.py#L109

cclauss

RuntimeError: CUDA error: out of memory

4

  

qtw1998

Training on custom dataset (9 classes)

3

Hi, I am facing issue in biFpn module while starting the training using pretrained d1. File "train.py", line 238, in train() File "train.py", line 183, in train classification, regression, anchors...

dvlshah

This project looks great! Thanks for the effort. I tried to run `demo.py` and ran into several dependency issues. Also, I would recommend that you fix the version numbers of...

jjhbw

configs/efficientdet-d0.zxt _Originally posted by @rinaldiodoy in https://github.com/toandaominh1997/EfficientDet.Pytorch/issues/66#issuecomment-570847300_

rinaldiodoy

an error in eval.py

7

get_augmentation func has no phase named 'valid', so eval.py throws a runtimeerror.

kapness

can you tell me your albumentations version?? I got AttributeError: module 'albumentations.augmentations.transforms' has no attribute 'RandomResizedCrop'

limengfei3675

when I load pretrained model EfficientDet-D1(with Weight)

7

RuntimeError: Error(s) in loading state_dict for EfficientDet: size mismatch for bbox_head.retina_cls.weight: copying a param with shape torch.Size([180, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([9, 256,...

XDhughie

Hello, thanks for your code.My torchvision version is 0.4.2 and cuda version is 10.1. When I run demo.py I get a error : RuntimeError: CUDA error: no kernel image is...

limengfei3675

Where is the constrcit of Flops?

10

EfficientNet can be constricted by FLOPS you know

qtw1998