Tensorflow Repo for "DeepGCNs: Can GCNs Go as Deep as CNNs?"

Related tags

Deep Learning 3d-point-clouds geometric-deep-learning graph-neural-networks deep-gcns
Overview

DeepGCNs: Can GCNs Go as Deep as CNNs?

In this work, we present new ways to successfully train very deep GCNs. We borrow concepts from CNNs, mainly residual/dense connections and dilated convolutions, and adapt them to GCN architectures. Through extensive experiments, we show the positive effect of these deep GCN frameworks.

[Project] [Paper] [Slides] [Tensorflow Code] [Pytorch Code]

Overview

We do extensive experiments to show how different components (#Layers, #Filters, #Nearest Neighbors, Dilation, etc.) effect DeepGCNs. We also provide ablation studies on different type of Deep GCNs (MRGCN, EdgeConv, GraphSage and GIN).

Further information and details please contact Guohao Li and Matthias Müller.

Requirements

Conda Environment

In order to setup a conda environment with all neccessary dependencies run,

conda env create -f environment.yml

Getting Started

You will find detailed instructions how to use our code for semantic segmentation of 3D point clouds, in the folder sem_seg. Currently, we provide the following:

  • Conda environment
  • Setup of S3DIS Dataset
  • Training code
  • Evaluation code
  • Several pretrained models
  • Visualization code

Citation

Please cite our paper if you find anything helpful,

@InProceedings{li2019deepgcns,
    title={DeepGCNs: Can GCNs Go as Deep as CNNs?},
    author={Guohao Li and Matthias Müller and Ali Thabet and Bernard Ghanem},
    booktitle={The IEEE International Conference on Computer Vision (ICCV)},
    year={2019}
}

@misc{li2019deepgcns_journal,
    title={DeepGCNs: Making GCNs Go as Deep as CNNs},
    author={Guohao Li and Matthias Müller and Guocheng Qian and Itzel C. Delgadillo and Abdulellah Abualshour and Ali Thabet and Bernard Ghanem},
    year={2019},
    eprint={1910.06849},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

License

MIT License

Acknowledgement

This code is heavily borrowed from PointNet and EdgeConv. We would also like to thank 3d-semantic-segmentation for the visualization code.

Comments
  • Graph convolution

    Graph convolution

    hi, @lightaime I'm a beginner in GCN. In many papers, I see that GCN has a graph Laplacian matrix, but you don't seem to use it. How do you implement graph convolution?

    opened by Ericjiejie 9
  • The error, please help me.

    The error, please help me.

    When I run the code, I have not download the dataset Stanford3dDataset_v1.2_Aligned_Version.zip. I just use S3DIS. The error occured as fellow:

    2021-02-21 05:14:43.910830: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 1 Chunks of size 3932160 totalling 3.75MiB
2021-02-21 05:14:43.910862: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 6 Chunks of size 8388608 totalling 48.00MiB
2021-02-21 05:14:43.910895: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 1 Chunks of size 11665408 totalling 11.12MiB
2021-02-21 05:14:43.910927: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 3 Chunks of size 14680064 totalling 42.00MiB
2021-02-21 05:14:43.910960: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 2 Chunks of size 33554432 totalling 64.00MiB
2021-02-21 05:14:43.910992: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 1 Chunks of size 37748736 totalling 36.00MiB
2021-02-21 05:14:43.911024: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 54 Chunks of size 134217728 totalling 6.75GiB
2021-02-21 05:14:43.911057: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 1 Chunks of size 136314880 totalling 130.00MiB
2021-02-21 05:14:43.911090: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 1 Chunks of size 209643264 totalling 199.93MiB
2021-02-21 05:14:43.911122: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 6 Chunks of size 268435456 totalling 1.50GiB
2021-02-21 05:14:43.911158: I tensorflow/core/common_runtime/bfc_allocator.cc:641] 4 Chunks of size 536870912 totalling 2.00GiB
2021-02-21 05:14:43.911191: I tensorflow/core/common_runtime/bfc_allocator.cc:645] Sum Total of in-use chunks: 10.79GiB
2021-02-21 05:14:43.911226: I tensorflow/core/common_runtime/bfc_allocator.cc:647] Stats: 
Limit:                 12044415796
InUse:                 11584530176
MaxInUse:              11584530176
NumAllocs:                     590
MaxAllocSize:            856752640

2021-02-21 05:14:43.911371: W tensorflow/core/common_runtime/bfc_allocator.cc:271] *************************************************************************************************___
2021-02-21 05:14:43.911439: W tensorflow/core/framework/op_kernel.cc:1273] OP_REQUIRES failed at topk_op.cc:92 : Resource exhausted: OOM when allocating tensor with shape[1073742079] and type int8 on /job:localhost/replica:0/task:0/device:GPU:1 by allocator GPU_1_bfc
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1334, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1319, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1073742079] and type int8 on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[{{node tower_0/TopKV2_7}} = TopKV2[T=DT_FLOAT, _class=["loc:@tower_0/cond_7/strided_slice_2/Switch"], sorted=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Neg_7, tower_0/TopKV2_7/k)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

         [[{{node tower_0/gradients/AddN_30/_1927}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_8956_tower_0/gradients/AddN_30", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train.py", line 346, in <module>
    train()
  File "train.py", line 289, in train
    train_one_epoch(sess, ops, train_writer)
  File "train.py", line 333, in train_one_epoch
    feed_dict=feed_dict)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1152, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1328, in _do_run
    run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1348, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1073742079] and type int8 on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node tower_0/TopKV2_7 (defined at /home/deep_gcns-master/deep_gcns-master/utils/tf_util.py:672)  = TopKV2[T=DT_FLOAT, _class=["loc:@tower_0/cond_7/strided_slice_2/Switch"], sorted=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Neg_7, tower_0/TopKV2_7/k)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

         [[{{node tower_0/gradients/AddN_30/_1927}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_8956_tower_0/gradients/AddN_30", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.


Caused by op 'tower_0/TopKV2_7', defined at:
  File "train.py", line 346, in <module>
    train()
  File "train.py", line 222, in train
    dilations=DILATIONS)
  File "/home/deep_gcns-master/deep_gcns-master/sem_seg/model.py", line 55, in __init__
    dilations)
  File "/home/deep_gcns-master/deep_gcns-master/sem_seg/model.py", line 102, in build_gcn_backbone_block
    is_training=self.is_training)
  File "/home/deep_gcns-master/deep_gcns-master/gcn_lib/gcn_utils.py", line 47, in build
    is_training=is_training)
  File "/home/deep_gcns-master/deep_gcns-master/gcn_lib/tf_edge.py", line 41, in dilated_knn_graph
    neigh_idx = tf_util.knn(dists, k=k*dilation)
  File "/home/deep_gcns-master/deep_gcns-master/utils/tf_util.py", line 672, in knn
    _, nn_idx = tf.nn.top_k(neg_adj, k=k)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/nn_ops.py", line 2359, in top_k
    return gen_nn_ops.top_kv2(input, k=k, sorted=sorted, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 7701, in top_kv2
    "TopKV2", input=input, k=k, sorted=sorted, name=name)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
    self._traceback = tf_stack.extract_stack()

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1073742079] and type int8 on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
         [[node tower_0/TopKV2_7 (defined at /home/deep_gcns-master/deep_gcns-master/utils/tf_util.py:672)  = TopKV2[T=DT_FLOAT, _class=["loc:@tower_0/cond_7/strided_slice_2/Switch"], sorted=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Neg_7, tower_0/TopKV2_7/k)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

         [[{{node tower_0/gradients/AddN_30/_1927}} = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_8956_tower_0/gradients/AddN_30", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

    Errors keep popping up, the code doesn't stop, it just keeps reporting errors and looping through EPOACH001. Please help me ,thank you!

    opened by jiaruHithub 8
  • Error occurs when run 'sh train_job.sh' with 1 TitanX (gpu:12GB)

    Error occurs when run 'sh train_job.sh' with 1 TitanX (gpu:12GB)

    ......

    **** EPOCH 001 ****

    Current batch/total batch num: 0/9949 2019-06-08 19:12:55.361276: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-06-08 19:12:55.437713: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-06-08 19:13:01.682376: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-06-08 19:13:01.729082: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-06-08 19:13:04.594699: E tensorflow/stream_executor/cuda/cuda_dnn.cc:363] Loaded runtime CuDNN library: 7.0.5 but source was compiled with: 7.1.4. CuDNN library major and minor version needs to match or have higher minor version in case of CuDNN 7.0 or later version. If using a binary install, upgrade your CuDNN library. If building from sources, make sure the library loaded at runtime is compatible with the version specified during compile configuration. 2019-06-08 19:13:04.595317: W ./tensorflow/stream_executor/stream.h:2093] attempting to perform DNN operation using StreamExecutor without DNN support Traceback (most recent call last): File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1741, in main() File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1735, in main globals = debugger.run(setup['file'], None, None, is_module) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1135, in run pydev_imports.execfile(file, globals, locals) # execute the script File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 333, in train() File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 275, in train train_one_epoch(sess, ops, train_writer) File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 320, in train_one_epoch feed_dict=feed_dict) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run run_metadata) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InternalError: cudnn PoolBackward launch failed [[node tower_0/gradients/tower_0/maxpool/maxpool_grad/MaxPoolGrad (defined at /media/zgh/winz/3D/deep_gcns/sem_seg/train.py:223) = MaxPoolGrad[T=DT_FLOAT, data_format="NHWC", ksize=[1, 4096, 1, 1], padding="VALID", strides=[1, 2, 2, 1], _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/adj_conv_final/Relu, tower_0/maxpool/maxpool, tower_0/gradients/tower_0/Tile_28_grad/Sum)]] [[{{node tower_0/gradients/AddN_147/_2879}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_19645_tower_0/gradients/AddN_147", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

    Caused by op u'tower_0/gradients/tower_0/maxpool/maxpool_grad/MaxPoolGrad', defined at: File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1741, in main() File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1735, in main globals = debugger.run(setup['file'], None, None, is_module) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1135, in run pydev_imports.execfile(file, globals, locals) # execute the script File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 333, in train() File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 223, in train grads = trainer.compute_gradients(loss) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/training/optimizer.py", line 519, in compute_gradients colocate_gradients_with_ops=colocate_gradients_with_ops) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 630, in gradients gate_gradients, aggregation_method, stop_gradients) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 814, in _GradientsHelper lambda: grad_fn(op, *out_grads)) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 408, in _MaybeCompile return grad_fn() # Exit early File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py", line 814, in lambda: grad_fn(op, *out_grads)) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_grad.py", line 607, in _MaxPoolGrad data_format=op.get_attr("data_format")) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 5081, in max_pool_grad data_format=data_format, name=name) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func return func(*args, **kwargs) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1770, in init self._traceback = tf_stack.extract_stack()

    ...which was originally created as op u'tower_0/maxpool/maxpool', defined at: File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/runrunrun/pycharm-community-2019.1.1/helpers/pydev/pydevd.py", line 1741, in main() [elided 2 identical lines from previous traceback] File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 333, in train() File "/media/zgh/winz/3D/deep_gcns/sem_seg/train.py", line 204, in train skip_connect=SKIP_CONNECT) File "/media/zgh/winz/3D/deep_gcns/sem_seg/model.py", line 50, in init fusion = self.build_fusion_block(graphs, num_vertices) File "/media/zgh/winz/3D/deep_gcns/sem_seg/model.py", line 115, in build_fusion_block out_max = tf_util.max_pool2d(out, [num_vertices, 1], padding='VALID', scope='maxpool') File "/media/zgh/winz/3D/deep_gcns/utils/tf_util.py", line 381, in max_pool2d name=sc.name) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 2140, in max_pool name=name) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 4641, in max_pool data_format=data_format, name=name) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func return func(*args, **kwargs) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/media/zgh/df7f0859-33fc-4a7e-afef-851b5c4f4005/zgh/3D/.virtualenvs/py2te112/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1770, in init self._traceback = tf_stack.extract_stack()

    InternalError (see above for traceback): cudnn PoolBackward launch failed [[node tower_0/gradients/tower_0/maxpool/maxpool_grad/MaxPoolGrad (defined at /media/zgh/winz/3D/deep_gcns/sem_seg/train.py:223) = MaxPoolGrad[T=DT_FLOAT, data_format="NHWC", ksize=[1, 4096, 1, 1], padding="VALID", strides=[1, 2, 2, 1], _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/adj_conv_final/Relu, tower_0/maxpool/maxpool, tower_0/gradients/tower_0/Tile_28_grad/Sum)]] [[{{node tower_0/gradients/AddN_147/_2879}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_19645_tower_0/gradients/AddN_147", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

    We've got an error while stopping in post-mortem: <type 'exceptions.KeyboardInterrupt'>

    Process finished with exit code 1

    Could you help me? Thank you very much!

    opened by zhangguanghui1 8
  • the obj file can not open

    the obj file can not open

    i got the prediction visualization file and the groudtruth file,but i can not open them with maya or 3D Max,my process of achieve files as follows python batch_inference.py --model_path log/epoch_30.ckpt --dump_dir log/dump -- output_filelist log/output_filelist.txt --room_data_filelist meta/area5_data_label.txt --visu and the epoch_30.ckpt is acquired through training the S3DIS dataset the zip package is the obj files(_gt,_pred)，hope you can help me ,thanks a lot! dump.zip

    opened by wangziningabc 3
  • why the inpus_ph default to shape=(batch_size, num_vertices, 9)?

    why the inpus_ph default to shape=(batch_size, num_vertices, 9)?

    Hi! As your write in inputs_ph = tf.placeholder(tf.float32, shape=(batch_size, num_vertices, 9)).

    Why it is default to 9? where is the 9 from? I think the 3D point cloud should be 3.

    If I wish to use the model to my own point cloud dataset with (x,y,z) coordinates => 3， should I change the original code to shape=(batch_size, num_vertices, 3)?

    thanks!

    opened by zem007 2
  • Have you test deep_gcns on ppi dataset?

    Have you test deep_gcns on ppi dataset?

    opened by wjlpku 2
  • missing 'meta/anno_paths.txt'

    missing 'meta/anno_paths.txt'

    I download dataset and unzip into data/. And run the collect_indoor3d_data.py, it shows: Traceback (most recent call last): File "collect_indoor3d_data.py", line 6, in <module> import indoor3d_util File "/deep_gcns/sem_seg/indoor3d_util.py", line 14, in <module> g_classes = [x.rstrip() for x in open(os.path.join(BASE_DIR, 'meta/class_names.txt'))] FileNotFoundError: [Errno 2] No such file or directory: '/deep_gcns/sem_seg/meta/class_names.txt'

    opened by guozhiyao 1
  • ImportError: cannot import name 'scale_translate_pointcloud' from 'utils'

    ImportError: cannot import name 'scale_translate_pointcloud' from 'utils'

    In PyTorch code, when I try to run the train code of Part Segmentation on PartNet, I got this issue, can you help?

    Traceback (most recent call last): File "main.py", line 13, in from utils import scale_translate_pointcloud ImportError: cannot import name 'scale_translate_pointcloud' from 'utils' (/home/jrl/Github/deep_gcns_torch-master/examples/part_sem_seg/../../utils/init.py)

    opened by AshWYL 0
  • Use ==/!= to compare str, bytes, and int literals

    Use ==/!= to compare str, bytes, and int literals

    Identity is not the same thing as equality in Python.

    $ python

    >>> layer_name = 'knn_'
>>> layer_name += 'graph'
>>> layer_name == 'knn_graph'
True
>>> layer_name is 'knn_graph'
False
    opened by cclauss 0
  • The environment errors when run the script 'sh +x train_job.sh'

    The environment errors when run the script 'sh +x train_job.sh'

    **** EPOCH 001 ****

    Current batch/total batch num: 0/1243 2019-09-18 09:37:40.102211: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-09-18 09:37:40.303894: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-09-18 09:37:42.000486: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 0, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-09-18 09:37:42.117158: E tensorflow/core/grappler/optimizers/dependency_optimizer.cc:666] Iteration = 1, topological sort failed with message: The graph couldn't be sorted in topological order. 2019-09-18 09:37:44.299611: E tensorflow/stream_executor/cuda/cuda_blas.cc:652] failed to run cuBLAS routine cublasSgemmBatched: CUBLAS_STATUS_EXECUTION_FAILED 2019-09-18 09:37:44.299648: E tensorflow/stream_executor/cuda/cuda_blas.cc:2574] Internal: failed BLAS call, see log for details Traceback (most recent call last): File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1334, in _do_call return fn(*args) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1319, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1407, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape=[8,4096,3], b.shape=[8,3,4096], m=4096, n=4096, k=3, batch_size=8 [[{{node tower_0/MatMul}} = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Squeeze, tower_0/transpose)]] [[{{node tower_1/adj_conv_27/bn/cond/add/_4375}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device_incarnation=1, tensor_name="edge_25108_tower_1/adj_conv_27/bn/cond/add", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

    During handling of the above exception, another exception occurred:

    Traceback (most recent call last): File "train.py", line 327, in train() File "train.py", line 270, in train train_one_epoch(sess, ops, train_writer) File "train.py", line 314, in train_one_epoch feed_dict=feed_dict) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run run_metadata_ptr) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1152, in _run feed_dict_tensor, options, run_metadata) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1328, in _do_run run_metadata) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1348, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InternalError: Blas xGEMMBatched launch failed : a.shape=[8,4096,3], b.shape=[8,3,4096], m=4096, n=4096, k=3, batch_size=8 [[node tower_0/MatMul (defined at /disk/tia/tia/deep_gcns/utils/tf_util.py:655) = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Squeeze, tower_0/transpose)]] [[{{node tower_1/adj_conv_27/bn/cond/add/_4375}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device_incarnation=1, tensor_name="edge_25108_tower_1/adj_conv_27/bn/cond/add", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

    Caused by op 'tower_0/MatMul', defined at: File "train.py", line 327, in train() File "train.py", line 203, in train skip_connect=SKIP_CONNECT) File "/disk/tia/tia/deep_gcns/sem_seg/model.py", line 49, in init skip_connect) File "/disk/tia/tia/deep_gcns/sem_seg/model.py", line 82, in build_gcn_backbone_block is_training=self.is_training) File "/disk/tia/tia/deep_gcns/gcn_lib/gcn_utils.py", line 50, in build is_training=is_training) File "/disk/tia/tia/deep_gcns/gcn_lib/tf_edge.py", line 40, in dilated_knn_graph dists = distance_metric(vertex_features) File "/disk/tia/tia/deep_gcns/utils/tf_util.py", line 655, in pairwise_distance point_cloud_inner = tf.matmul(point_cloud, point_cloud_transpose) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 2019, in matmul a, b, adj_x=adjoint_a, adj_y=adjoint_b, name=name) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 1245, in batch_mat_mul "BatchMatMul", x=x, y=y, adj_x=adj_x, adj_y=adj_y, name=name) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func return func(*args, **kwargs) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op op_def=op_def) File "/home/data/anaconda3/envs/lmt36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in init self._traceback = tf_stack.extract_stack()

    InternalError (see above for traceback): Blas xGEMMBatched launch failed : a.shape=[8,4096,3], b.shape=[8,3,4096], m=4096, n=4096, k=3, batch_size=8 [[node tower_0/MatMul (defined at /disk/tia/tia/deep_gcns/utils/tf_util.py:655) = BatchMatMul[T=DT_FLOAT, adj_x=false, adj_y=false, _device="/job:localhost/replica:0/task:0/device:GPU:0"](tower_0/Squeeze, tower_0/transpose)]] [[{{node tower_1/adj_conv_27/bn/cond/add/_4375}} = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:1", send_device_incarnation=1, tensor_name="edge_25108_tower_1/adj_conv_27/bn/cond/add", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

    My environment is CUDA 9.0; cudnn 7.4; tensorflow-gpu 1.12.0 with two 2080ti Can you help me with this problem?

    opened by limt15 2
Owner
Guohao Li
PhD student at KAUST IVUL.
Guohao Li
GitHub
Repo for my Tensorflow/Keras CV experiments. Mostly revolving around the Danbooru20xx dataset

SW-CV-ModelZoo Repo for my Tensorflow/Keras CV experiments. Mostly revolving around the Danbooru20xx dataset Framework: TF/Keras 2.7 Training SQLite D

null 20 Dec 27, 2022
Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy.

Deploy tensorflow graphs for fast evaluation and export to tensorflow-less environments running numpy. Now with tensorflow 1.0 support. Evaluation usa

Marcel R. 349 Aug 6, 2022
TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

null 2.6k Jan 4, 2023
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Peter Lin 6.5k Jan 4, 2023
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Robust Video Matting (RVM) English | 中文 Official repository for the paper Robust High-Resolution Video Matting with Temporal Guidance. RVM is specific

flow-dev 2 Aug 21, 2022
Official Repo for Ground-aware Monocular 3D Object Detection for Autonomous Driving

Visual 3D Detection Package: This repo aims to provide flexible and reproducible visual 3D detection on KITTI dataset. We expect scripts starting from

Yuxuan Liu 305 Dec 19, 2022
AI grand challenge 2020 Repo (Speech Recognition Track)

KorBERT를 활용한 한국어 텍스트 기반 위협 상황인지(2020 인공지능 그랜드 챌린지) 본 프로젝트는 ETRI에서 제공된 한국어 korBERT 모델을 활용하여 폭력 기반 한국어 텍스트를 분류하는 다양한 분류 모델들을 제공합니다. 본 개발자들이 참여한 2020 인공지

Young-Seok Choi 23 Jan 25, 2022
This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TransUNet This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation Usage

null 1.4k Jan 4, 2023
This repo provides the official code for TransBTS: Multimodal Brain Tumor Segmentation Using Transformer (https://arxiv.org/pdf/2103.04430.pdf).

TransBTS: Multimodal Brain Tumor Segmentation Using Transformer This repo is the official implementation for TransBTS: Multimodal Brain Tumor Segmenta

Raymond 247 Dec 28, 2022
Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura, Hiroki Ohashi, and Tomoaki Yosh

null 105 Dec 23, 2022
Official repo for QHack—the quantum machine learning hackathon

Note: This repository has been frozen while we consider the submissions for the QHack Open Hackathon. We hope you enjoyed the event! Welcome to QHack,

Xanadu 118 Jan 5, 2023
This repo is customed for VisDrone.

Object Detection for VisDrone(无人机航拍图像目标检测) My environment 1、Windows10 (Linux available) 2、tensorflow >= 1.12.0 3、python3.6 (anaconda) 4、cv2 5、ensemble

null 53 Jul 17, 2022
This repo is customed for VisDrone.

Object Detection for VisDrone(无人机航拍图像目标检测) My environment 1、Windows10 (Linux available) 2、tensorflow >= 1.12.0 3、python3.6 (anaconda) 4、cv2 5、ensemble

null 53 Jul 17, 2022
The official repo of the CVPR2021 oral paper: Representative Batch Normalization with Feature Calibration

Representative Batch Normalization (RBN) with Feature Calibration The official implementation of the CVPR2021 oral paper: Representative Batch Normali

Open source projects of ShangHua-Gao 76 Nov 9, 2022
A repo with study material, exercises, examples, etc for Devnet SPAUTO

MPLS in the SDN Era --> DevNet SPAUTO Get right to the study material: Checkout the Wiki! A lab topology based on MPLS in the SDN era book used for 30

Hugo Tinoco 67 Nov 16, 2022
The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

Dice Loss for NLP Tasks This repository contains code for Dice Loss for Data-imbalanced NLP Tasks at ACL2020. Setup Install Package Dependencies The c

null 223 Dec 17, 2022
This repo contains the official code of our work SAM-SLR which won the CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.

Skeleton Aware Multi-modal Sign Language Recognition By Songyao Jiang, Bin Sun, Lichen Wang, Yue Bai, Kunpeng Li and Yun Fu. Smile Lab @ Northeastern

Isen (Songyao Jiang) 128 Dec 8, 2022
This repo is developed for Strong Baseline For Vehicle Re-Identification in Track 2 Ai-City-2021 Challenges

A STRONG BASELINE FOR VEHICLE RE-IDENTIFICATION This paper is accepted to the IEEE Conference on Computer Vision and Pattern Recognition Workshop(CVPR

Cybercore Co. Ltd 78 Dec 29, 2022
Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation"

SharinGAN Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation" The official project we

Koutilya PNVR 23 Oct 19, 2022