-
有没有具体指标可以参考下
-
@jeffreykuang Hi there,
FCENet seems promising, the following are some questions:
- FCENet uses ResNet50 backbone, but why doesn't it use a ResNet18 backbone with a better architecture such as:
[DD…
-
Is mlp in this figure really linear layer? Or it is a conv1d layer.
![image](https://user-images.githubusercontent.com/16894837/117428082-4e441680-af58-11eb-9da3-f43ec09892da.png)
-
Hi,
I train model in Google Colab and i bug:
![image](https://user-images.githubusercontent.com/80568515/118233869-bd6fbc80-b4bc-11eb-8def-98b75352919f.png)
Can you help me?
Thanks you so much!
-
Could you share your training log?
I used the ddrnet23_slim's default setting (experiments/cityscapes/ddrnet23_slim.yaml) with 1000 Epochs but got only 0.6223 mIoU.
thanks.
=> saving checkpoint…
-
Hi
Going through your code, I cannot seem to find these two classes which are referred to in [DDRNET_39.py ](https://github.com/ydhongHIT/DDRNet/blob/main/segmentation/DDRNet_39.py)
These do no…
-
I build the "DDRNet23 Slim" model that you provided. I have images with shape of 1024 H x 1024 W x 3 C. There are 8 different classes in my dataset. When I check model summary with `summary(net.cuda()…
-
I have read your CVPR'2020. Both the idea and the results are impressive. Will you release the code of this paper recently?