EfficientDet.Pytorch

EfficientDet.Pytorch copied to clipboard

Gradient computation error

2

Hello When I run the train.py module, I get this error: `RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [3, 3]],...

siaavashZ

已经解决了win10下关于pytorch-EfficientDet下训练自己数据集的问题

2

已经解决了win10下关于pytorch-EfficientDet下训练自己数据集的问题，如有不了解的，可以交流 关于pytorch-EfficientDet，可加群857449786 注明（pytorch EfficientDet）共同学习，谢谢

QQ2737499951

I found a problem.there is a size mismatch problem. This is my input:  After the input of size 35, the following error appears:   

hammerAttack

Kindly share config file for coco data set with network efficientdet-d7 Thanks, Ajmal

ma-siddiqui

efficientdet-d7 weight file

5

Hi, Where I can find your trained model weight file for efficientdet-d7? Thanks, Ajmal

ma-siddiqui

can you gave me the file 'checkpoint_VOC_efficientdet-d1_34.pth'

1

wuyangdut

How to download checkpoint_VOC_efficientdet-d1_34.pth

1

Hi, everyone~ It seems that the url for downloading the pretrained weights is broken. So how can I download the pretrained model checkpoint_VOC_efficientdet-d0_268.pth or checkpoint_VOC_efficientdet-d1_34.pth? Thanks!

OwalnutO

minji-o-j

train my datasets , IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed

1

File "/home/ubuntu/EfficientDet.Pytorch-master/datasets/augmentation.py", line 113, in __call__ annots[:, :4] *= scale IndexError: too many indices for array: array is 1-dimensional, but 2 were indexed

Wangyy-moya

When I trained the code on my dataset, the mAP always kept 0.0.

3

When I trained the code on my dataset, the mAP always kept 0.0. My dataset had 17 classes, how can I fix it? Hope to your reply. `mAP: len(VOC_CLASSES): 17...

Williamwsk