fferroni / pointpillars Goto Github PK

View Code? Open in Web Editor NEW

47.0 47.0 17.0 27 KB

Point Pillars 3D detection network implementation in Tensorflow

License: GNU General Public License v3.0

CMake 0.31% Python 56.22% C++ 43.47%

pointpillars's People

Contributors

Stargazers

Watchers

Forkers

jasonlee020 collector-m ryotamono yangyongguang yif-chen lawrencekiba ramizka polynomialqian xiaocongcsu chasingw oladimeji-bello lhzlhz mengziyang-doing scrouzet zwu-um yalagamsrinivas

pointpillars's Issues

Please tell how to visualise the output

Get ERROR msg "'unicode' object is not callable" when I implement my test script.

Hello, I'm new to tensorflow keras api and 3d object detection.
When I call tf.keras.models.load_model() func after training the model, got the following error msg which make me confusion:

Traceback (most recent call last):
  File "/home/xxx/tensorflow/PointPillars-master/test.py", line 24, in <module>
    pillar_net_trained = tf.keras.models.load_model(os.path.join(log_dir, "finished.h5"))
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/saving.py", line 235, in load_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/saving.py", line 325, in model_from_config
    return deserialize(config, custom_objects=custom_objects)
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/layers/serialization.py", line 74, in deserialize
    printable_module_name='layer')
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 192, in deserialize_keras_object
    list(custom_objects.items())))
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/network.py", line 1273, in from_config
    process_node(layer, node_data)
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/network.py", line 1231, in process_node
    layer(input_tensors[0], **kwargs)
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/engine/base_layer.py", line 554, in __call__
    outputs = self.call(inputs, *args, **kwargs)
  File "/home/xxx/.local/lib/python2.7/site-packages/tensorflow/python/keras/layers/core.py", line 743, in call
    return self.function(inputs, **arguments)
  File "/home/xxx/tensorflow/PointPillars-master/network.py", line 33, in <lambda>
    if batch_size > 1:
TypeError: 'unicode' object is not callable

In File "/home/xxx/tensorflow/PointPillars-master/network.py", there are these codes around line 33:

    if batch_size > 1:
        corrected_indices = tf.keras.layers.Lambda(lambda t: correct_batch_indices(t, batch_size))(input_indices)
    else:
        corrected_indices = input_indices

The training process stucked at the second epoch

My training process stucked at the second epoch, did anyone encounter this problem?

Can make some detail in Readme?

Can show some detial of this code ?

Does anyone get an optimal result on KITTI?

Cannot find any possible results on KITTI, I am wondering if someone already reproduce the results of original paper.

Please write readme file to setup project

Trouble with running prediction after training

Hi,

I modified the point_pillars_training.py file to save the model as pb as follows: pillar_net.save('point_pillars1.pb')
I also changed the parameters in config.py to a batch size of 2 and to run 20 epochs for training. After I run the training on an RTX 2080, I tried running the point_pillars_prediction.py file to get the following output:

File "<dir_to_pointpillars>/PointPillars/processors.py", line 155, in getitem
lidar = self.data_reader.read_lidar(self.lidar_files[i])
IndexError: list index out of range

Here is what I have installed:
Tensorflow: 2.1.0
Keras: 2.4.3
OpenCV-Python: 4.2.0.34
CUDA: 10.1

I have the save_model.pb saved in the root dir, while the model.h5 is saved under '/logs'. Anyone know what the issue is?

how to setup

when i run

python setup.py build

it outputs

(tf1.15) sc@sc:~/disk/git/PointPillars$ python setup.py build
running build
running build_ext
CMake Error at CMakeLists.txt:3 (add_subdirectory):
  The source directory

    /home/sc/disk/git/PointPillars/pybind11

  does not contain a CMakeLists.txt file.


CMake Error at CMakeLists.txt:4 (pybind11_add_module):
  Unknown CMake command "pybind11_add_module".


-- Configuring incomplete, errors occurred!
See also "/home/sc/disk/git/PointPillars/build/temp.linux-x86_64-3.6/CMakeFiles/CMakeOutput.log".
Traceback (most recent call last):
  File "setup.py", line 67, in <module>
    zip_safe=False,
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/site-packages/setuptools/__init__.py", line 144, in setup
    return distutils.core.setup(**attrs)
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/core.py", line 148, in setup
    dist.run_commands()
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 955, in run_commands
    self.run_command(cmd)
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/command/build.py", line 135, in run
    self.run_command(cmd_name)
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/cmd.py", line 313, in run_command
    self.distribution.run_command(command)
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/distutils/dist.py", line 974, in run_command
    cmd_obj.run()
  File "setup.py", line 33, in run
    self.build_extension(ext)
  File "setup.py", line 57, in build_extension
    subprocess.check_call(['cmake', ext.sourcedir] + cmake_args, cwd=self.build_temp, env=env)
  File "/home/sc/anaconda3/envs/tf1.15/lib/python3.6/subprocess.py", line 311, in check_call
    raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['cmake', '/home/sc/disk/git/PointPillars', '-DCMAKE_LIBRARY_OUTPUT_DIRECTORY=/home/sc/disk/git/PointPillars/build/lib.linux-x86_64-3.6', '-DPYTHON_EXECUTABLE=/home/sc/anaconda3/envs/tf1.15/bin/python', '-DCMAKE_BUILD_TYPE=Release']' returned non-zero exit status 1.

how to solve this?

Decode process error

My decode process of the network is wrong even if with the ground truth as input. The bounding boxes of the decode output were not in the right place. Could any one share me a copy of the decode code?
My email is [email protected].
Thanks very much!

Inconsistent units of bounding box yaws

In config.py, the yaws are written in radians, but in point_pillars_test.py they're in degrees.

Is this a bug or am I missing something ?

What Is The Version of Tensorflow or Keras？

Hello，I‘ve get error msg：
Traceback (most recent call last):
File "point_pillars_training_run.py", line 52, in
workers=1)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/engine/training.py", line 2312, in fit_generator
callbacks.on_epoch_begin(epoch)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/callbacks.py", line 80, in on_epoch_begin
callback.on_epoch_begin(epoch, logs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/keras/_impl/keras/callbacks.py", line 596, in on_epoch_begin
lr = self.schedule(epoch)
TypeError: () missing 1 required positional argument: 'lr'

Could u please tell us the right version ？

Results on kitti

Hi Francesco,
Do you reproduce the results of the point pillars paper on kitti dataset (I have not seen some metrics, like mAP) ?
In a first time, I have implemented on the side a non maximum suppression after the network to compare the predicted box and GT. But I have a doubt on your angle implementation. Like in second paper, I have tried Yawlabel - YanAnchor in ground truth generation and then something like soomthL1(sin(Ypred - Ygt)) but the network doesn't seem to be able to predict angles at all.
Do you test it on your side ?
best regards
Pierre