guanyonglai

因为我在Python3运行，所以要做一些小的修改，， win10-64、CPU环境， 1.utils/visualize.py 44行：win=unicode(name) --> win=str(name) 2.main.py 22行： 加 import config 3.main.py 108行：loss_meter.add(loss.data[0]) --> loss_meter.add(loss.item()) 4.config.py 10行：load_model_path = 'checkpoints/model.pth' --> load_model_path = None 5.config.py 12行：batch_size = 128 --> batch_size =...

弱弱问一下和另外一篇HRNet的代码什么关系

3

另外一份开源代码：https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation

请问这个GEN只针对market数据吗

6

duke，cuhk，或者我自己的数据能达到这个效果吗

train my own data, the results is mussy

1

I used this project to train human segmentation data, change the num_class and .odgt file, but the results is mussy. Are there any other changes that need to be made

我有训好的模型和做好的alpha图

6

希望大家一起改进，参考我的博客： https://blog.csdn.net/guanyonglai/article/details/104559189

a trained model is here

5

but results doesn't look very good, I trained the model on 15000 alpha imgs, it is too slow to get alpha 链接: https://pan.baidu.com/s/1Iepf6C7saX-ytyu-Dd0OAA 提取码: m6cb

why my test img only has outline

2

 why my test img is like this? only has outline

Is there something wrong with this model? The result picture is here: 链接：https://pan.baidu.com/s/1kyQWIj71n2xweUKCgmTzDA 提取码：ls77

运行出结果了，还没看明白啥意思

6

********** Data initialization complete. Initializing model... Model initialization complete. Loading the model of iteration 80000... Transforming... *feature_list 1759 Evaluating... Evaluation complete. Cost: 0:00:20.782591 ===Rank-1 (Include identical-view cases)=== NM: 98.642, BG:...