-
### Description
Suddenly the connection gets adjusted and it says
[09:32:16] Server instructed us to use an audio codec different from Opus, which is no longer supported. Disconnecting...
[09:3…
-
_base_: '../_base_/ade20k.yml'
batch_size: 3
iters: 120000
train_dataset:
transforms:
- type: ResizeStepScaling
min_scale_factor: 0.5
max_scale_factor: 2.0
scale_st…
-
@ydhongHIT I downloaded pretrained model for ddrnet23(cityscapes). I want to try this model on two images. As you see in below code, I resized images to (1024,2048,3) like mentioned in paper. The `get…
-
if the scale of input is 256*256, should I rescale it to a large size? Scale 1024*1024 or something.
-
### 💡 Your Question
I found a file in the repository, cityscapes_ddrnet.yaml. Where it is described in detail how to train ddrnet on the cityscapes dataset.
```yaml
# Instructions:
# 0. Make sur…
-
@tianyu0207 Your work is excellent. When I tried to reproduce the results using the cityscapes_best.pth pre-trained weights that you provided for training, I found that very good performance was alrea…
-
### 🐛 Describe the bug
I'm using a file [cityscapes_ddrnet.yaml.](https://github.com/Deci-AI/super-gradients/blob/master/src/super_gradients/recipes/cityscapes_ddrnet.yaml) This file contains detaile…
-
您好，看到了您在回复其他人问题的时候说，您是把训练和验证集合成了大的训练集（train+val=2975+500）去训练的，您有没有尝试过仅仅使用原始训练集train(2975)去做训练，我仅使用训练集train，ddrnet_23_silm的miou仅能达到74左右
-
The error was occured after changing batch_size from 8 to 4 in cityscapes.yaml.
Found 2975 train images.
Found 500 val images.
Epoch: [1/500] Iter: [1/185] LR: 0.00010049 Loss: 7.71337414: 1%|…
-
hi，thanks for your work and sharing.
i download the DDRNet_23_slim pre-trained weights on camvid datasets. However, it can't parse images and obtain accurate semantic segmentation results by normali…