-
你好：
我在用模版的时候，发现正文的字体有时候突然自动加粗，把这个部分换个位置就又正常了，不知道是啥原因。。。
-
Hi @cxa9264 ,
Sorry to distrub you. I found that you set --n_epochs=200, --n_epochs_decay=200, which makes the first stage of the style change take a long time, possibly more than 2 days. I wonder …
-
Thank you for this work! Could you point me to the implementation of deeplab you used for your paper?
-
Hello, currently, most papers perform post-processing with denseCRF when comparing performance. I would like to ask how to implement denseCRF optimization for the localization maps and segmentation re…
-
The pretrained on Scan-Net DeepLab checkpoint link is broken.
-
### Bug description
I struggle with this warning (multiplied 512 times on 512 gpus):
```
pytorch_lightning/trainer/connectors/data_connector.py:442: PossibleUserWarning: The dataloader,
val…
-
图像分类：
- [x] RepVGG
- [x] ConvNeXt
- [x] MobileViT
目标检测：
- [x] 补上YOLOv4网络讲解
- [x] 补上YOLOv5网络讲解（没有论文）
- [x] 补上YOLOX网络讲解
- [x] 补上Faster RCNN换backbone视频
- [x] FCOS 模型讲解
语义分割：
- [x] Deep…
-
I'm working on optimizing inference speed on a custom dataset that I wrote that is based on both the Panoptic-DeepLab (resnet50 backbone) and the kMaX-DeepLab (convnext backbone) approaches. This cust…
-
您好，我按照readme产生了pseudo_seg_labels，miou是70.3，将伪掩码拿去deeplabv2_resnet监督训练（这里我将train_aug.txt中的所有SegmentationClassAug目录换成了所有pseudo_seg_labels目录），训练之后测试阶段加载得到的checkpoint_final.pth，但是在val上的结果非常差，miou只有22%左右，不…
-