-
How can I lock the uniform sampling option for training network with command "> python -m runx.runx scripts/train_cityscapes.yml -i"?
I tried to modify a config and train file in the code and lock t…
-
`AttributeError Traceback (most recent call last)
in
5 import torch
6 from mmcv import Config
----> 7 from mmdet.apis import inference_detector, init_detector, show_resu…
-
While trying to reproduce the results of the paper "Context Encoders: Feature Learning by Inpainting", using the torch code available in Github repositories with adversarial loss, I got the following …
-
In fact, i only have one GPU.So if i want to run inference and dump images on a folder of images,what part of the code do I need to change.
-
您好！
我有训练得到的.pth文件，也有yaml文件，但是您知道如何推理单张图片，得到可视化的结果吗？因为我看官网的网络都只有test，并没有写如何推理单张的图片。您能告诉我吗？
非常感谢
z0v0z updated
6 months ago
-
Hi!
First of all, thanks for releasing the code.
In algorithm 1, in the paper, it says only X_s and Y_s are used. However, in "Pixel-level Adversarial and Constraint-based Adaptation" they use X…
-
I try to run and debug train.py in VSCode, but fails to set the right arguments. What should it be like?
My args are like this:
"version": "0.2.0",
"configurations": [
{
"name": "Py…
-
My GPU is a K80 12GB, but the cuda said the memory is not big enough. Could you please tell me how much GPU memory do you need for the fcn scores in the cityscapes？ Thank you @junyanz
-
Hi,
What are the hyperparameters used for training the SOTA model on train+val? I tried the SOTA hyperparams in the repository with cv=3 instead of 0, but I'm getting poor results on the testset (~84…
-
directory tree should be look like this:
```
├── list
│ ├── cityscapes
│ │ ├── test.lst
│ │ ├── trainval.lst
│ │ └── val.lst
│ ├── lip
│ │ ├── testvalList.txt
│ │ ├── …