isl-org
Input key error in 3d object detection example
Using master (12/04/2021) + bypassing tensor_requirements to be 2.4.1+ on ubuntu 20.04 = successful data visualization on data reader example using semantic KITTI dataset.
After downloading the KITTI data/label/calib as per dataset python script, I'm running the following example for the point pillars
import os import open3d.ml as _ml3d
import open3d.ml.tf as ml3d
cfg_file = "/content/point_pillars/Open3D-ML/ml3d/configs/pointpillars_kitti.yml" cfg = _ml3d.utils.Config.load_from_file(cfg_file)
model = ml3d.models.PointPillars(**cfg.model) cfg.dataset['dataset_path'] = "/content/KITTI_DATASET/KITTI_PTCLOUD_DATA/data_object_velodyne" dataset = ml3d.datasets.KITTI(cfg.dataset.pop('dataset_path', None), **cfg.dataset)
pipeline = ml3d.pipelines.ObjectDetection(model, dataset=dataset, device="gpu", **cfg.pipeline)
ckpt_path = '/content/KITTI_DATASET/pointpillars_kitti_202012221652utc/ckpt-12'
pipeline.load_ckpt(ckpt_path=ckpt_path)
test_split = dataset.get_split("test")
data = test_split.get_data(0)
result = pipeline.run_inference(data)
pipeline.run_test() '''
Yields the following error (most of them warnings for not having CUDA):
2021-12-04 21:22:00.545338: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2021-12-04 21:22:00.545360: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. 2021-12-04 21:22:01.339405: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2021-12-04 21:22:01.339424: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. 2021-12-04 21:22:01.908347: I tensorflow/compiler/jit/xla_cpu_device.cc:41] Not creating XLA devices, tf_xla_enable_xla_devices not set 2021-12-04 21:22:01.908474: W tensorflow/stream_executor/platform/default/dso_loader.cc:60] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory 2021-12-04 21:22:01.908485: W tensorflow/stream_executor/cuda/cuda_driver.cc:326] failed call to cuInit: UNKNOWN ERROR (303) 2021-12-04 21:22:01.908501: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (dsohn03): /proc/driver/nvidia/version does not exist 2021-12-04 21:22:01.908649: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2021-12-04 21:22:01.909075: I tensorflow/compiler/jit/xla_gpu_device.cc:99] Not creating XLA devices, tf_xla_enable_xla_devices not set INFO - 2021-12-04 21:22:02,104 - object_detection - Restored from /home/daniel.sohn/Desktop/KITTI_DATASET/pointpillars_kitti_202012221652utc/ckpt-12 INFO - 2021-12-04 21:22:02,105 - kitti - Found 7518 pointclouds for test Traceback (most recent call last): File "./demo_ptpillars.py", line 37, in
result = pipeline.run_inference(data) File "/content/point_pillars/env/lib/python3.8/site-packages/open3d/_ml3d/tf/pipelines/object_detection.py", line 57, in run_inference results = model(data, training=False) File "/content/point_pillars/env/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py", line 1012, in call outputs = call_fn(inputs, *args, **kwargs) File "/content/point_pillars/env/lib/python3.8/site-packages/open3d/_ml3d/tf/models/point_pillars.py", line 142, in call inputs = unpack(inputs[0], inputs[-2]) KeyError: 0
Is this a repeat issue of https://github.com/isl-org/Open3D-ML/issues/408 ?
tensorflow 2.4.4 open3d 0.13.0
Thank you,
Could you please try with the latest version of Open3D (0.14.1) which was released two days ago?
Thanks for the reply. The issue is still there with tf 2.5.2 + open3D 0.14.1 on MASTER branch.
File "/content/point_pillars/env/lib/python3.8/site-packages/open3d/_ml3d/tf/models/point_pillars.py", line 142, in call inputs = unpack(inputs[0], inputs[-2]) KeyError: 0
FYI, I've extracted the lidar datas (3 categories) to the same folder - /content/KITTI_DATASET/KITTI_PTCLOUD_DATA/ contains "data_object_velodyne", "data_object_label_2", and "data_object_calib" on the same level.
Package Version
absl-py 0.15.0 addict 2.4.0 anyio 3.4.0 argon2-cffi 21.1.0 astunparse 1.6.3 attrs 21.2.0 Babel 2.9.1 backcall 0.2.0 bleach 4.1.0 cachetools 4.2.4 certifi 2021.10.8 cffi 1.15.0 charset-normalizer 2.0.9 cycler 0.11.0 debugpy 1.5.1 decorator 5.1.0 defusedxml 0.7.1 deprecation 2.1.0 entrypoints 0.3 flatbuffers 1.12 fonttools 4.28.3 gast 0.4.0 google-auth 2.3.3 google-auth-oauthlib 0.4.6 google-pasta 0.2.0 grpcio 1.34.1 h5py 3.1.0 idna 3.3 importlib-metadata 4.8.2 importlib-resources 5.4.0 ipykernel 6.6.0 ipython 7.30.1 ipython-genutils 0.2.0 ipywidgets 7.6.5 jedi 0.18.1 Jinja2 3.0.3 joblib 1.1.0 json5 0.9.6 jsonschema 4.2.1 jupyter-client 7.1.0 jupyter-core 4.9.1 jupyter-packaging 0.11.1 jupyter-server 1.12.1 jupyterlab 3.2.4 jupyterlab-pygments 0.1.2 jupyterlab-server 2.8.2 jupyterlab-widgets 1.0.2 keras-nightly 2.5.0.dev2021032900 Keras-Preprocessing 1.1.2 kiwisolver 1.3.2 Markdown 3.3.6 MarkupSafe 2.0.1 matplotlib 3.5.0 matplotlib-inline 0.1.3 mistune 0.8.4 nbclassic 0.3.4 nbclient 0.5.9 nbconvert 6.3.0 nbformat 5.1.3 nest-asyncio 1.5.4 notebook 6.4.6 numpy 1.19.5 oauthlib 3.1.1 open3d 0.14.1 opt-einsum 3.3.0 packaging 21.3 pandas 1.3.4 pandocfilters 1.5.0 parso 0.8.3 pexpect 4.8.0 pickleshare 0.7.5 Pillow 8.4.0 pip 21.3.1 pkg_resources 0.0.0 prometheus-client 0.12.0 prompt-toolkit 3.0.23 protobuf 3.19.1 ptyprocess 0.7.0 pyasn1 0.4.8 pyasn1-modules 0.2.8 pycparser 2.21 Pygments 2.10.0 pyparsing 3.0.6 pyrsistent 0.18.0 python-dateutil 2.8.2 pytz 2021.3 PyYAML 6.0 pyzmq 22.3.0 requests 2.26.0 requests-oauthlib 1.3.0 rsa 4.8 scikit-learn 1.0.1 scipy 1.7.3 Send2Trash 1.8.0 setuptools 59.5.0 setuptools-scm 6.3.2 six 1.15.0 sniffio 1.2.0 tensorboard 2.7.0 tensorboard-data-server 0.6.1 tensorboard-plugin-wit 1.8.0 tensorflow 2.5.2 tensorflow-estimator 2.5.0 termcolor 1.1.0 terminado 0.12.1 testpath 0.5.0 threadpoolctl 3.0.0 tomli 1.2.2 tomlkit 0.7.2 tornado 6.1 tqdm 4.62.3 traitlets 5.1.1 typing-extensions 3.7.4.3 urllib3 1.26.7 wcwidth 0.2.5 webencodings 0.5.1 websocket-client 1.2.1 Werkzeug 2.0.2 wheel 0.37.0 widgetsnbextension 3.5.2 wrapt 1.12.1 zipp 3.6.0
This example runs for PyTorch, not for Tensorflow. To work with Tensorflow, we need to "batchify" the data.
`test_dataset = dataset.get_split('validation') test_split = TFDataloader(dataset=test_dataset, model=model, use_cache=False)
test_loader, len_test = test_split.get_loader(batch_size=1,transform=False) print(len_test) for it in test_loader: boxes = pipeline.run_inference(it)[0] print(boxes)`