EfficientDet.Pytorch

EfficientDet.Pytorch copied to clipboard

Training on own dataset

16

Is it possible to train the network on my own dataset?

ammaradel

training dataset include images with non-labeled objects that I do not want to detect

1

My training dataset include images with non-labeled objects that I do not want to detect, I use xml without bounded box in training. but there is an error, File "/root/EfficientDet.Pytorch/datasets/augmentation.py",...

jfkkf123

Update README.md

2

Removed the typo for efficientdet

abhiksark

infer time

2

any bady can give the infer time for the b0---b7. thanks.

GreenTeaHua

EfficientNet backbones are not reachable

3

When I try to train the EfficientNet-D0 model, I run into an issue when it hits the ```load_pretrained_weights``` function in ```models/utils.py```. The code returns a HTTP 403 when trying to...

hodgka

detect result

10

您好，这边测试了一个weights/checkpoint_VOC_efficientdet-d1_37.pth的模型，结果是这个样子的，有几个好像未检测到 

zhanglaplace

The below lines with torch.ones and torch.zeros in the focus loss are allocating arrays on one device and then transfering them to gpu using .cuda. This is inefficient especially in...

rmcavoy

Some problems in calculating mAP in eval.py

4

Hi,thank you for your sharing~ When I use this project training the VOCdataset, I can use the demo.py to test the pictures, but when using eval.py calculating mAP, I get...

Cynthia-324

I tried to train efficientdet -d1 model on VOC dataset and got low mAP. mAP: aeroplane: 0.37774546979552437 bicycle: 0.2717609619189093 bird: 0.07373408655526852 boat: 0.11174968193861216 bottle: 0.03085867327429357 bus: 0.3259476835112142 car: 0.4270658513682306 cat:...

quangtn266

test with video

1

I found the test result is worse than YOLOv3

tslgithub