-
我使用cityscapes数据集训练，PR值都还好，但是看了一下results文件夹下产生的pre_img发现语义分割都画乱了，之后我自己又下载了一下你的模型，看一下图片检测结果，发现也不行。我不知道是我根据网络输出结果把语义分割画到原图的过程错误还是有忽略其他什么问题，希望您可以给一个将神经网络结果画回原图的示例代码。谢谢！
"
import cv2
import numpy as…
-
在window下执行python ./train.py --batch_size=1 -- --use_gpu False --parallel True --train_crop_size=769 --total_step=50 --norm_type=gn --init_weights_path=./deeplabv3plus_gn_init --save_weights_path=model…
-
Hi, sorry to bother you, but there is an attribute prantik_avgpool in DeepLabV3Plus in line 254(c1_avgpool = self.prantik_avgpool(c1)), that you didn't mention before
-
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.
…
-
paddlepaddle框架版本：1.3
model库代码：最新
**运行环境：p40,4卡**
训练命令：
```bash
python ./train.py --batch_size=8 --parallel=true --train_crop_size=769 --total_step=90000 --init_weights_path=./deeplabv3plus_xcepti…
-
Hi, author. What are the mIoUs in the final segmentation results that did not using the SAM for the post processing in V3+ and SwinL, respectively? And also I want to know, what are the mIoUs in final…
-
Traceback (most recent call last):
File "train.py", line 340, in
trainer = Trainer(args)
File "train.py", line 167, in __init__
aux=args.aux, norm_layer=BatchNorm2d).to(self.device)
…
-
Hello everyone, I used predictability. py to infer the 1_image 23_image and 114_image in the samples folder, and the results of the inference test were very poor. The instructions for executing the in…
-
When i want to export my retrained model by export_model.py supported by office, i have a difficult problem,please help me!
I run this shell:
```
python export_model.py \
--checkpoint_path="/hom…
-
Hi, very impressed by your work!
I don't find exactly the same IoU when I run your configs files for training (for CityScapes, around 80% versus 81%; for LIP, around 55% versus 58%). I was wondering…