EfficientDet.Pytorch

EfficientDet.Pytorch copied to clipboard

y78h11b09

How many parameters do you have?

4

From what I read in the paper, the effectivedet-d0 standard was 3.9m. But your model comes in 10.2m on a d0 basis. Did I calculate the parameters correctly? model =...

HansolEom

run demo.py, image nothing happened

7

Hi, thanks very much for your code! I trained a model 'checkpoint_VOC_efficientdet-d2_17.pth' on my own dataset, but when I demo.py this model no box appeared in the image. Nothing happened...

shengyuqing

where D_class use?

5

you have defined D_class in efficientdet，but i don't find you have used it in net?

shenjun1994

Double normalization in weighted feature fusion

2

In `BiFPN.forward()` the feature weights are normalized: https://github.com/toandaominh1997/EfficientDet.Pytorch/blob/fbe56e58c9a2749520303d2d380427e5f01305ba/models/bifpn.py#L178-L180 In calculating the bottom up and top down features, it appears this normalization is done again unnecessarily: https://github.com/toandaominh1997/EfficientDet.Pytorch/blob/fbe56e58c9a2749520303d2d380427e5f01305ba/models/bifpn.py#L190 https://github.com/toandaominh1997/EfficientDet.Pytorch/blob/fbe56e58c9a2749520303d2d380427e5f01305ba/models/bifpn.py#L196

oadams

6G GPU memory,batch_size=1 with D1 network,still got CUDA out of memory

11

Your default batch size is 32,What GPU did you used for training?

AlexLuya

The latest version of opencv >= 4.2 results in the following error when trying to run demo.py with a webcam: > qt.qpa.plugin: Could not find the Qt platform plugin "cocoa"...

harpalsahota

training efficientDet-d0 over VOC0712 dataset, cpu cost is very high, always over 85%. can anybody tell me what happens ? thanks

3

y78h11b09

Any trained models for EfficientDet D1~D7?

1

Can anybody provide the trained models of EfficientDet D1~D7 for eval ? Thanks !

opentld

How to convert to onnx model?

1

@toandaominh1997 Hi, thanks for your Great work. I have tried to convert efficientdet-b0.pth to onnx model, and my code is follow : ``` def to_onnx(checkpoint_name,save_onnx_name='efficientdet.onnx', size_image=(512, 512)): from torch.autograd import...

SHMathRabbit