Comments (9)
File "D:\dgcnn.pytorch-master\data.py", line 149, in load_data_semseg
test_area_name = "Area_" + test_area
TypeError: can only concatenate str (not "NoneType") to str
I have set test_area = ‘1’ but when printing it output 'none' in the terminal
from dgcnn.pytorch.
I think the path "D:\dgcnn.pytorchV2\data/stanford_indoor3d\Stanford3dDataset_v1.2_Aligned_Version\Area_1_conferenceRoom_1.txt" should be "D:\dgcnn.pytorchV2\data\stanford_indoor3d\Stanford3dDataset_v1.2_Aligned_Version\Area_1_conferenceRoom_1.txt"
from dgcnn.pytorch.
Thanks a lot! I used '//' to replace all the'', and finally generated .npy in the folder. These files are not in the correct directory, I need to move them manually. The previous error was due to the gen_indoor3d_h5.py not running correctly.
What's more, pred = seg_pred.max(dim=2)[1](in main_semseg.py, line 111) leads to the following error:
IndexError: Dimension out of range (expected to be in range of [-2, 1], but got 2)
I have noticed in the main_cls.py, the parameter is dim=1. Could you please explain the difference?
from dgcnn.pytorch.
By the way, after the terminal outputs 'Let's use 1 GPUs! Use SGD', there is no new output for about two hours. Is this a normal phenomenon?
from dgcnn.pytorch.
Please use the batch size --batch_size
larger than 1.
from dgcnn.pytorch.
Could you give me some information about the training time on the task of semseg with 1 GPUs and batch size is 32, for the full dataset?
from dgcnn.pytorch.
Because I use 4 GPUs, I can't provide the training time for 1 GPU.
from dgcnn.pytorch.
Could you tell me your training time for reference?Thanks in advance
from dgcnn.pytorch.
I remember the time is less than one day.
from dgcnn.pytorch.
Related Issues (20)
- how to set the value of K with different points for other datasets HOT 1
- How long you take to train a epoch in S3DIS? I want to know it. Thank you! HOT 1
- 代码运行结果,比原来的要高很多 HOT 7
- Hello, I would like to ask, how do you test the miou of each class_names in the semantic segmentation content? HOT 4
- 请问model的get_graph_feature中这一段代码是不是没有什么作用 HOT 2
- How to visualize a category or an area in an S3DIS room HOT 7
- 作者您好,请问是否可以看一下您在ScanNet数据集中的data目录? HOT 2
- 3d coordinates + extra feature HOT 1
- problems about transfer learning HOT 4
- Fine Tuning partseg DGCNN
- Problem with visualization(semseg)
- Can DGCNN be converted to ONNX model? HOT 2
- 引入更多的采样点以增加模型的细节 HOT 3
- Why the implemented network architecture is different with the architecture in the paper? HOT 1
- about dataset
- ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (1201,) + inhomogeneous part.
- Don't find the file `from config import CLASS_NAMES`.
- No data inside raw_data3d
- the error results for Visualization(比较严重的可视化结果)
- problems with Semantic Segmentation on the S3DIS Dataset
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from dgcnn.pytorch.