-
## 背景
PyTorch 最近在 2.1.0 版本发布了 `torch.export` 功能,提供了以 PyTorch 2.x 的 dynamo 为核心的模型导出方法。其功能上与我们 Paddle 动转静模型导出 `paddle.jit.save` 相类似,因此我们想要建设一个 repo 能够自动对比 `torch.export` 和 `paddle.jit.save` 的导出成功与否,[…
-
Hi,@rishizek:
Thanks for your implementation of deeplabV3, but I cannot find the multigride architecture as you mentioned in the Evaluation of README file: "repo | MG(1,2,4)+ASPP(6,12,18)+Image P…
-
I am getting the below error in the testing module.
> InvalidArgumentError (see above for traceback): assertion failed: [`labels` out of bound] [Condition x < y did not hold element-wise:x (mean_io…
-
Hi Xingang, could I ask some questions about the SCNN?
1. What is spatial cross entropy loss in training mentioned in paper?
2. Are labels pixel level segmentation of the same size as input image?
…
-
Hello , i tested inference speed and compared it with simple torchvision resnet50 .
I used 2080ti and pytorch 1.4
Results are :
torchvision resnet50 - 13-15 ms
axial-resnet-s - 79-81ms
But in t…
cszer updated
4 years ago
-
I am trying to use wider_resnet trunk by setting the following in scripts/train_cityscapes.yml:
snapshot: "ASSETS_PATH/seg_weights/wider_resnet38.pth.tar",
arch: wider_resnet.wider_resnet38_a2,
…
-
参考来源:
```
https://blog.csdn.net/qq_35759272/article/details/123700919
```
使用deeplabv3+训练自己的数据集:
```
https://blog.csdn.net/weixin_39357271/article/details/124078660
```
-
i implement the heatmap and paf generate as operators. https://github.com/li-haoran/mxnet-cmu_pose, and implement some image data augmentations method. and train with different lr_mult.
now noly on …
-
Dear Wei Feng,
Thanks for your Work, I am currently using your codebase trying to reproduce your model performence and have encountered several issues while executing the `run_all_configs.sh` scr…
-
hello, I was using this set of custom nodes until recently when i tried updating (after a while of not updating). I'm suddenly unable to use them, even after uninstalling and reinstalling and installi…