-
Hi, what's the batch size and learning rate for the pretrained fast-scnn model from here: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_4x8_80k_lr0.12_cityscapes-f5096c79.pth
…
-
## ❓ Question
How to solve aten::floor converter not found?
## What you have already tried
I am trying to convert a jit trace of a Fast SCNN network into TensorRT. I've confirmed that the t…
-
@Tramac @BorisTestov @prianchoI try to use the coco dataset and only include two classes person and background , when I train ,the errors are follows:
_File "train.py", line 203, in
trainer.t…
-
Thank you for contributing to PaddlePaddle.
Before submitting the issue, you could search issue in the github in case that th
If there is no solution,please make sure that this is an inference issue…
-
我使用分割套件在平台上训练fast scnn 出现了GPU利用率特别低的情况（CPU利用率，内存都还正常）
-
There was no such problem during the first training. The same data set for the second training is reported as follows：
`Namespace(aux=False, aux_weight=0.4, base_size=1, batch_size=2, crop_size=768…
-
Hello, you list Fast-SCNN in the models, but I don't find it in code. Is Fast-SCNN supported?
-
Thanks for your error report and we appreciate it a lot.
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
…
-
Really Awesome work Thank you pretty much ！！！
(1) I adjust the provided pretrained model of CUlane_resnet34 on my small coarsely annotated dataset and it alreadly works pretty awesome even though the…
-
## 综述
- (2020) Image Segmentation Using Deep Learning:A Survey [[paper]](https://arxiv.org/pdf/2001.05566.pdf)
- The 2018 DAVIS Challenge on Video Object Segmentation [[paper]](https://arxiv.org…