-
Hello!
I'm using mmsegmentation to train models on the ADE20K dataset. However, I cannot download the ADE20K dataset, since I found the [link](https://github.com/open-mmlab/mmsegmentation/blob/mas…
-
When I use customed dataset, this error occurs.
1. Complete issue
```shell
Traceback (most recent call last):
File "C:\Anaconda3\envs\mmseg\lib\site-packages\mmengine\registry\build_functions.py…
-
I tried two commits on ade's commit server. The first time I successfully uploaded and got the evaluation result, the second I got an error, but I observed the structure of the two zips locally withou…
-
hi, any exp result on comparasion with yolov5? Retinanet itself didn't quite fast on mobile platform.
How about mAP compare with yolov5-tiny?
-
in deeplabv3plus ade20k training Is layer wise decay used?
in mmsegmentation training log (https://download.openmmlab.com/mmsegmentation/v0.5/deeplabv3plus/deeplabv3plus_r101-d8_512x512_80k_ade20k/d…
-
Where is block annotations for pascal VOC
-
Hi,
Thank you for your consideration.
I am running this evaluation code with BestSeg Tiny checkpoint on ADE dataset, but I cannot see where is PQ showing in the output. Could you show me how I can g…
-
when i try "image_demo.py" an error occurred.
palette.shape =[19,3]
self.CLASSES=150
how do i fix it?
-
为什么ade20k数据集在训练和验证时输入网络的图片尺寸大小不一样，在输入Resnet50backbone的第一个layer时的featuremap的shape是[2,64,128,128],但在验证时同样位置的featuremap大小会变成[2,64,128,171]。我猜测是做了多尺度数据增广的原因，我尝试不使用多尺度数据增广，在test_pipeline中去除多尺度数据增广之后，并采用了 v…
-
hi,
Thanks for your time. I am trying to deploy the model in Xavier nx platform. I have built the environment and tested the deploy.py without quantization, it works fine.
But when i tried …