mmmmimic / diffconvnet Goto Github PK

Hi, thanks for sharing the code. I try to retrain the 3d scene segmentation task on my computer. I get some bugs when I start to train the model. show as below:
`Train 0, loss: 1.834570, train acc: 0.527190, train avg acc: 0.112260, train iou: 0.075878, mean iou: 0.479272

Test 0, loss: 1.757209, test acc: 0.546379, test avg acc: 0.111111, test iou: 0.068297, mean iou: 0.692278

Train 1, loss: 1.718582, train acc: 0.581674, train avg acc: 0.111090, train iou: 0.072744, mean iou: 0.69713

Test 1, loss: 1.735542, test acc: 0.546379, test avg acc: 0.111111, test iou: 0.068297, mean iou: 0.692278`
As you can see, the Test mean iou is not changed, it keeps the value stable (0.692278). Can you give me some suggestions?

radius = base_radius + (max_radius - base_radius)*kd_score

What max_radius means?

    Hi! max_radius here is 2(r^2), base_radius is r^2, thus radius = r^2 + (2*r^2 - r^2)*d = r^2*(1+d).

Originally posted by @mmmmimic in #4 (comment)
So, the root operation seems lost? Moreover, I find that the balanced renormalization is important in Table 5. Actually, after softmaxing, the range of A has been [0, 1], why further renormalize?

Hi, thanks for sharing the code. I try to retrain the 3d scene segmentation task on my computer. I get some bugs when I start to train the model. show as below:
`Train 0, loss: 1.834570, train acc: 0.527190, train avg acc: 0.112260, train iou: 0.075878, mean iou: 0.479272

Test 0, loss: 1.757209, test acc: 0.546379, test avg acc: 0.111111, test iou: 0.068297, mean iou: 0.692278

Train 1, loss: 1.718582, train acc: 0.581674, train avg acc: 0.111090, train iou: 0.072744, mean iou: 0.69713

Test 1, loss: 1.735542, test acc: 0.546379, test avg acc: 0.111111, test iou: 0.068297, mean iou: 0.692278`
As you can see, the Test mean iou is not changed, it keeps the value stable (0.692278). Can you give me some suggestions?

(diffconv)root@ailab-PowerEdge-T640:/home/ailab/diffconvNet#pvthon3 data_prep.py --dataset=toronto3d
Traceback (most recent call last):
File "data_prep.py", line 104, in
eval("download %s(data_dir)"%dataset)
File "", line 1, in
File "data_prep.py", ine 78, in download_toronto3d
split Toronto3D(i, data dir=data dir)
File "data_prep.py", line 7, in split_Toronto3D
import open3d .ml.torch as ml3d
File "/root/anaconda3/envs/diffconv/lib/python3.7/site-packages/open3d/ml/torch/ init.py", line 38, in
match_torch_ver = '.'.join( o3d torch version.release[:2] + ('*',))
TypeError: sequence item 0: expected str instance, int found

how to solve the question?

Thank you for your work！The results of my run on the dataset are shown in this figure. Obviously, I have encountered a problem. I hope you can help me with the answer. Thank you very much!

Hi
I am trying to download modelnet40_ply_hdf5_2048.zip. But its timeout.

--2023-08-16 13:56:19-- (try: 3) https://shapenet.cs.stanford.edu/media/modelnet40_ply_hdf5_2048.zip
Connecting to shapenet.cs.stanford.edu (shapenet.cs.stanford.edu)|171.67.77.19|:443... failed: Connection timed out.
Retrying.

when will you release the code? I want to replay your experiments and verify your idea.