-
Hello, I have a question I’d like to ask. I try to training this on my own dataset, but the loss often starts showing nan after 0-4 epochs. I’ve tried reducing the learning rate and applying gradient …
-
by follow zhe instruction on website i install the pagkage success
however,when i want to check whether it's right, some wrong happened
it reply that IndexError: list index out of range after …
-
Thank you for sharing the code, It is great work
I wonder if there any guiding scripts for training custom dataset with only one class.
-
Hi, I tried to run the training code with the 1m config but got significantly worse performance compared to the performance reported in the paper. I notice that you mentioned in the paper that batch s…
-
1. The oscillation of loss function is severe
2. The segmentation effect is not good when using your own dataset, and the Miou is too low
Why, I look forward to your reply
-
How can I achieve the human parsing task，Do you have any instructions？
xddlj updated
2 years ago
-
您好，我在加载cityscapes_M_pretrained预训练模型做**测试**时，发现logger中显示我load 0 parameters，于是我找到下面的代码
if imgnet_pretrained:
pretrained_state = torch.load(cfg.MODEL.PRETRAINED, map_location='cpu')['state_dic…
-
Hello,
I appreciate for your kind responses for every questions!
now I'm working on the implementations of all hardnet models, but I couldn't find the details of the **"first_channel" and "ch_list"…
-
## 环境
- 【FastDeploy版本】： 说明具体的版本，如fastdeploy-linux-gpu-1.0.4
- 【编译命令】自行编译C# API
- cmake .. -G "Visual Studio 16 2019" -A x64 -DENABLE_ORT_BACKEND=ON -DENABLE_PADDLE_BACKEND=ON -DENABLE_OPENVINO_…
-
When we performed the training, there are a lot of mistakes in trainUDA.py.