AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation

Thank you for the great work! I get this error below when I run: ./training/train_AE_AtlasNet.py

I checked two more similar issues but this looks different. Any idea how to solve it? Any help appreciated!

File "./training/train_AE_AtlasNet.py", line 151, in dist1, dist2 = distChamfer(points.transpose(2,1).contiguous(), pointsReconstructed) #loss function File "./training/train_AE_AtlasNet.py", line 64, in distChamfer P = (rx.transpose(2,1) + ry - 2*zz) RuntimeError: CUDA error: out of memory

I run pytorch:0.4.1 / Ubuntu 18.04

FULL CODE:

(pytorch-atlasnet) [email protected]:~/AtlasNet$ python ./training/train_AE_AtlasNet.py --env $env --nb_primitives $nb_primitives |& tee ${env}.txt Setting up a new session... Namespace(accelerated_chamfer=0, batchSize=32, env='AE_AtlasNet', model='', nb_primitives=25, nepoch=120, num_points=2500, super_points=2500, workers=12) Random Seed: 314 {'plane': '02691156', 'bench': '02828884', 'cabinet': '02933112', 'car': '02958343', 'chair': '03001627', 'monitor': '03211117', 'lamp': '03636649', 'speaker': '03691459', 'firearm': '04090263', 'couch': '04256520', 'table': '04379243', 'cellphone': '04401088', 'watercraft': '04530566'} category 02691156 files 4044 0.999752781211372 % category 02828884 files 1813 0.9983480176211453 % category 02933112 files 1571 0.9993638676844784 % category 02958343 files 3514 0.46878335112059766 % category 03001627 files 6778 1.0 % category 03211117 files 1093 0.9981735159817352 % category 03636649 files 2309 0.9961173425366695 % category 03691459 files 1597 0.9870210135970334 % category 04090263 files 2373 1.0 % category 04256520 files 3173 1.0 % category 04379243 files 8436 0.9914208485133388 % category 04401088 files 1050 0.9980988593155894 % category 04530566 files 1939 1.0 % {'plane': '02691156', 'bench': '02828884', 'cabinet': '02933112', 'car': '02958343', 'chair': '03001627', 'monitor': '03211117', 'lamp': '03636649', 'speaker': '03691459', 'firearm': '04090263', 'couch': '04256520', 'table': '04379243', 'cellphone': '04401088', 'watercraft': '04530566'} category 02691156 files 4044 0.999752781211372 % category 02828884 files 1813 0.9983480176211453 % category 02933112 files 1571 0.9993638676844784 % category 02958343 files 3514 0.46878335112059766 % category 03001627 files 6778 1.0 % category 03211117 files 1093 0.9981735159817352 % category 03636649 files 2309 0.9961173425366695 % category 03691459 files 1597 0.9870210135970334 % category 04090263 files 2373 1.0 % category 04256520 files 3173 1.0 % category 04379243 files 8436 0.9914208485133388 % category 04401088 files 1050 0.9980988593155894 % category 04530566 files 1939 1.0 % training set 31747 testing set 7943 **Traceback (most recent call last): File "./training/train_AE_AtlasNet.py", line 151, in <module> dist1, dist2 = distChamfer(points.transpose(2,1).contiguous(), pointsReconstructed) #loss function File "./training/train_AE_AtlasNet.py", line 64, in distChamfer P = (rx.transpose(2,1) + ry - 2*zz) RuntimeError: CUDA error: out of memory**

I compare our method with AtlasNet several times. I need to edit the source code each time. However, the latest code is very hard to understand because it is of high abstraction. It takes me an hour to understand the relationship between each module.

I run the demo succesfully but after I launch the visdom server

python -m visdom.server -p 8888

I am stuck, I can't write any command anymore in my anaconda window. How do I continue? thanks!

I tried to debug the chamfer.cu by printing the values of tensors. I created two point clouds containing 3 and 5 points, respectively. The values are shown as below.

(1,.,.) = 
 0.01 *
  0.0000  0.0000  0.0000
  -20.4838  4.4935  6.1395
  -3.7283 -0.7629  1.7736

(2,.,.) = 
 0.01 *
  0.0000  0.0000  0.0000
  -17.4992  4.4902  5.0518
  -1.6003 -1.2430  0.8040
[ Variable[CUDAType]{2,3,3} ]
(1,.,.) = 
  0.0051  0.1850  0.0004
  0.0051  0.1850  0.0093
  0.0096  0.1850  0.0081
  0.0096  0.1850  0.0016
  0.0075  0.1850  0.0004

(2,.,.) = 
 -0.1486 -0.0932 -0.0014
 -0.0406 -0.0932 -0.0017
 -0.2057 -0.0932 -0.0001
 -0.0915 -0.0932 -0.0001
  0.0103 -0.0932 -0.0001
[ Variable[CUDAType]{2,5,3} ]

I also add print statements in CUDA functions, and I got the following output.

2i = 0, n = 3, j = 0, k = 0, d = 0.03425420, x = (0.00000000 0.00000000 0.00000000) y = (0.00511124 0.18500790 0.00038808)
2i = 0, n = 3, j = 1, k = 0, d = 0.06742091, x = (-0.20483765 0.04493479 0.06139540) y = (0.00511124 0.18500790 0.00038808)
2i = 0, n = 3, j = 2, k = 0, d = 0.03920735, x = (-0.03728317 -0.00762936 0.01773610) y = (0.00511124 0.18500790 0.00038808)
2i = 1, n = 3, j = 0, k = 0, d = 0.03573948, x = (-0.08192606 0.01907521 0.02376382) y = (0.00749534 0.18500790 0.00928491)
2i = 1, n = 3, j = 1, k = 0, d = 0.03405631, x = (-0.00152916 0.00097788 -0.00109852) y = (0.00749534 0.18500790 0.00928491)
2i = 1, n = 3, j = 2, k = 0, d = 0.03437031, x = (0.00000000 0.00000000 0.00000000) y = (0.00749534 0.18500790 0.00928491)
2i = 0, n = 3, j = 0, k = 1, d = 0.03434026, x = (0.00000000 0.00000000 0.00000000) y = (0.00511124 0.18500790 0.00928491)
2i = 0, n = 3, j = 1, k = 1, d = 0.06641452, x = (-0.20483765 0.04493479 0.06139540) y = (0.00511124 0.18500790 0.00928491)
2i = 0, n = 3, j = 2, k = 1, d = 0.03897782, x = (-0.03728317 -0.00762936 0.01773610) y = (0.00511124 0.18500790 0.00928491)
2i = 1, n = 3, j = 0, k = 1, d = 0.03490656, x = (-0.08192606 0.01907521 0.02376382) y = (0.00231482 0.18500790 0.00713918)
2i = 1, n = 3, j = 1, k = 1, d = 0.03394968, x = (-0.00152916 0.00097788 -0.00109852) y = (0.00231482 0.18500790 0.00713918)
2i = 1, n = 3, j = 2, k = 1, d = 0.03428425, x = (0.00000000 0.00000000 0.00000000) y = (0.00231482 0.18500790 0.00713918)
2i = 0, n = 3, j = 0, k = 2, d = 0.03438481, x = (0.00000000 0.00000000 0.00000000) y = (0.00955979 0.18500790 0.00809300)
2i = 0, n = 3, j = 1, k = 2, d = 0.06842789, x = (-0.20483765 0.04493479 0.06139540) y = (0.00955979 0.18500790 0.00809300)
2i = 0, n = 3, j = 2, k = 2, d = 0.03939636, x = (-0.03728317 -0.00762936 0.01773610) y = (0.00955979 0.18500790 0.00809300)
2i = 1, n = 3, j = 0, k = 2, d = 0.03508088, x = (-0.08192606 0.01907521 0.02376382) y = (0.00231482 0.18500790 0.00253408)
2i = 1, n = 3, j = 1, k = 2, d = 0.03389502, x = (-0.00152916 0.00097788 -0.00109852) y = (0.00231482 0.18500790 0.00253408)
2i = 1, n = 3, j = 2, k = 2, d = 0.03423970, x = (0.00000000 0.00000000 0.00000000) y = (0.00231482 0.18500790 0.00253408)
2i = 0, n = 3, j = 0, k = 3, d = 0.03432181, x = (0.00000000 0.00000000 0.00000000) y = (0.00955979 0.18500790 0.00158027)
2i = 0, n = 3, j = 1, k = 3, d = 0.06916460, x = (-0.20483765 0.04493479 0.06139540) y = (0.00955979 0.18500790 0.00158027)
2i = 0, n = 3, j = 2, k = 3, d = 0.03956439, x = (-0.03728317 -0.00762936 0.01773610) y = (0.00955979 0.18500790 0.00158027)
2i = 1, n = 3, j = 0, k = 3, d = 0.03652760, x = (-0.08192606 0.01907521 0.02376382) y = (0.01075170 0.18500790 0.00364473)
2i = 1, n = 3, j = 1, k = 3, d = 0.03404036, x = (-0.00152916 0.00097788 -0.00109852) y = (0.01075170 0.18500790 0.00364473)
2i = 1, n = 3, j = 2, k = 3, d = 0.03435681, x = (0.00000000 0.00000000 0.00000000) y = (0.01075170 0.18500790 0.00364473)
3i = 0, n = 3, j = 0, k = 4, d = 0.03428425, x = (0.00000000 0.00000000 0.00000000) y = (0.00749534 0.18500790 0.00038808)
3i = 0, n = 3, j = 1, k = 4, d = 0.06842767, x = (-0.20483765 0.04493479 0.06139540) y = (0.00749534 0.18500790 0.00038808)
3i = 0, n = 3, j = 2, k = 4, d = 0.03941518, x = (-0.03728317 -0.00762936 0.01773610) y = (0.00749534 0.18500790 0.00038808)
3i = 1, n = 3, j = 0, k = 4, d = 0.03643737, x = (-0.08192606 0.01907521 0.02376382) y = (0.01075170 0.18500790 0.00602855)
3i = 1, n = 3, j = 1, k = 4, d = 0.03406866, x = (-0.00152916 0.00097788 -0.00109852) y = (0.01075170 0.18500790 0.00602855)
3i = 1, n = 3, j = 2, k = 4, d = 0.03437987, x = (0.00000000 0.00000000 0.00000000) y = (0.01075170 0.18500790 0.00602855)
i = 0, n = 3, j = 0, best = 0.03425420, best_i = 0
i = 0, n = 3, j = 1, best = 0.06641452, best_i = 1
i = 0, n = 3, j = 2, best = 0.03897782, best_i = 1
i = 1, n = 3, j = 0, best = 0.03490656, best_i = 1
i = 1, n = 3, j = 1, best = 0.03389502, best_i = 2
i = 1, n = 3, j = 2, best = 0.03423970, best_i = 2

For batch 0 (i = 0), everything seems correct. However, for batch 1 (i = 1), the values of point clouds are not in the tensors. Is there something wrong with the code?

Hi Iam actually try to evaluate SVR Atlas pretrained model on RGB image(chair), my parameters are really similar to the demo and i got wird result (by view in chrom 3D viewer ). i used the demo grid generation. when i run your demo plane.jpg im my network i got good results in the 3Dviewer . can you please direct my how to evaluate RGB image?

In train_AE_Atlasnet.py, the test set is used as the validation set to choose the best model. The test set should never be used during training and especially not to choose the best model as this biases the results. It's probably more appropriate to report the results on the last training epoch if there was no validation set.

I downloaded the corresponding normalized mesh (Only 58Mb) from the link you provided. I found that the number of the mesh was much smaller than the corresponding point cloud. Could you please provide the full dataset of the corresponding normalized mesh? Thank you!

Hi! I'm trying to download the point cloud data provided in this link: https://cloud.enpc.fr/s/j2ECcKleA1IKNzk but the network fails every time I try to download.

Do you know what's going on or how to download them?

Thank you in advance!

I directly run the script 'train_AE_Atlasnet.py' without any modification. As you can see above, the performance is good on the training set, but quite poor on the validation set. The validation loss increases quickly and doesn't decrease.

I found that some of your point cloud dataset provided are missing. Could you provide all the point cloud dataset？ or Could you tell me how to generate the point cloud dataset？ Thank you!

I found that the unused self.dist1 and self.dist2 in the file "nndistance/functions/nnd.py" cause memory leaking in my environment. (Python 3.5.2 with Pytorch 0.4.0)

class NNDFunction(Function):
    def forward(self, xyz1, xyz2):
        dist1,dist2=cuda_compute_from(xyz1,xyz2)
        # following two lines cause memory leak
        self.dist1 = dist1
        self.dist2 = dist2
        return dist1, dist2

    def backward(self, graddist1, graddist2):
        gradxyz1,gradxyz2=grad_cuda_compute_from(graddist1,graddist2)
        return gradxyz1, gradxyz2

Hi，i'm soory to bother you again. When I ran the code as you explained, I got the following error： sh: 1: tmux: not found Setting up a new session... Exception in user code:

could you give me some advice？ The overall operation results in the terminal are as follows:

/home/yukon/anaconda3/envs/pymesh/bin/python "/media/yukon/Extreme SSD/AtlasNet-master/train.py" anshu: Namespace(SVR=False, activation='relu', anisotropic_scaling=False, batch_size=32, batch_size_test=32, bottleneck_size=1024, class_choice=['airplane'], data_augmentation_axis_rotation=False, data_augmentation_random_flips=False, demo=True, demo_input_path='./doc/pictures/plane_input_demo.png', dir_name='', env='Atlasnet', hidden_neurons=512, http_port=8891, id='0', loop_per_epoch=1, lr_decay_1=120, lr_decay_2=140, lr_decay_3=145, lrate=0.001, multi_gpu=[0], nb_primitives=1, nepoch=150, no_learning=False, no_metro=False, normalization='UnitBall', num_layers=2, number_points=2500, number_points_eval=2500, random_rotation=False, random_seed=False, random_translation=False, reload_decoder_path='', reload_model_path='', remove_all_batchNorms=False, run_single_eval=False, sample=True, shapenet13=False, start_epoch=0, template_type='SPHERE', train_only_encoder=False, visdom_port=8890, workers=0) Loaded compiled 3D CUDA chamfer distance Launching new visdom instance in port 8890 TMUX=0 tmux new-session -d -s visdom_server ; send-keys "/home/yukon/anaconda3/envs/pymesh/bin/python -m visdom.server -p 8890 > /dev/null 2>&1" Enter sh: 1: tmux: not found Launching new HTTP instance in port 8891 TMUX=0 tmux new-session -d -s http_server ; send-keys "/home/yukon/anaconda3/envs/pymesh/bin/python -m http.server -p 8891 > /dev/null 2>&1" Enter sh: 1: tmux: not found Setting up a new session... Exception in user code:

Traceback (most recent call last): File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connection.py", line 175, in _new_conn (self._dns_host, self.port), self.timeout, **extra_kw File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/util/connection.py", line 95, in create_connection raise err File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/util/connection.py", line 85, in create_connection sock.connect(sa) ConnectionRefusedError: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connectionpool.py", line 710, in urlopen chunked=chunked, File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connectionpool.py", line 398, in _make_request conn.request(method, url, **httplib_request_kw) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connection.py", line 239, in request super(HTTPConnection, self).request(method, url, body=body, headers=headers) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/http/client.py", line 1291, in request self._send_request(method, url, body, headers, encode_chunked) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/http/client.py", line 1337, in _send_request self.endheaders(body, encode_chunked=encode_chunked) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/http/client.py", line 1286, in endheaders self._send_output(message_body, encode_chunked=encode_chunked) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/http/client.py", line 1046, in _send_output self.send(msg) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/http/client.py", line 984, in send self.connect() File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connection.py", line 205, in connect conn = self._new_conn() File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connection.py", line 187, in _new_conn self, "Failed to establish a new connection: %s" % e urllib3.exceptions.NewConnectionError: <urllib3.connection.HTTPConnection object at 0x7f2834dcc2b0>: Failed to establish a new connection: [Errno 111] Connection refused

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/requests/adapters.py", line 450, in send timeout=timeout File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/connectionpool.py", line 788, in urlopen method, url, error=e, _pool=self, _stacktrace=sys.exc_info()[2] File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/urllib3/util/retry.py", line 592, in increment raise MaxRetryError(_pool, url, error or ResponseError(cause)) urllib3.exceptions.MaxRetryError: HTTPConnectionPool(host='localhost', port=8890): Max retries exceeded with url: /env/Atlasnetatlasnet_singleview_1_sphere_2atlasnet_singleview_1_sphere (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f2834dcc2b0>: Failed to establish a new connection: [Errno 111] Connection refused',))

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/visdom/init.py", line 695, in _send data=json.dumps(msg), File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/visdom/init.py", line 656, in _handle_post r = self.session.post(url, data=data) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/requests/sessions.py", line 577, in post return self.request('POST', url, data=data, json=json, **kwargs) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/requests/sessions.py", line 529, in request resp = self.send(prep, **send_kwargs) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/requests/sessions.py", line 645, in send r = adapter.send(request, **kwargs) File "/home/yukon/anaconda3/envs/pymesh/lib/python3.6/site-packages/requests/adapters.py", line 519, in send raise ConnectionError(e, request=request) requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=8890): Max retries exceeded with url: /env/Atlasnetatlasnet_singleview_1_sphere_2atlasnet_singleview_1_sphere (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f2834dcc2b0>: Failed to establish a new connection: [Errno 111] Connection refused',)) [Errno 111] Connection refused on_close() takes 1 positional argument but 3 were given New MLP decoder : hidden size 512, num_layers 2, activation relu Network weights loaded from ./training/trained_models/atlasnet_singleview_1_sphere/network.pth! Atlasnet generated mesh at ./doc/pictures/plane_input_demoAtlasnetReconstruction.ply!

Process finished with exit code 0

Hey! Sorry to disturb you again!

I want to know if there any effective tools by python to visulize .obj file and save it to .png (except for meshlab).

Thanks for your reply!

Hi i'm sorry to bother you again.
when I used the code you give me to trying to build metro distance, I found that it could not be compiled successfully. 
It will indicate that the system path cannot be found. The results are shown as follows:

could you please give some advice to solve this problem. thanks a lot!

Hi! Sorry for disturb you again.

I want to ask questions about train and test strategy. In your code, you set opt.shapenet13==True. So does it means that you first train your network on all categories and then test on each class to get the experiment metrics data of every single class.

Looking forward to your reply!

Hi @ThibaultGROUEIX, thank you for sharing the code.

When downloading checkpoint of the model using the trained_models/download_models.sh (https://cloud.enpc.fr/s/c27Df7fRNXW2uG3/download) related to the version 2.2 of the source code, the link seems to be broken or no longer available. Could you please help me with this?

Thanks.