kendricktan / suiron Goto Github PK

Hi Kendrick, thanks for sharing your amazing project.
I have some problem when I'm running Train.py
here is the log :

data = pd.DataFrame.from_csv(filename)
Traceback (most recent call last):
File "train.py", line 18, in
c_x, c_servo = get_servo_dataset(d)
File "/Users/theamircoder/suiron/suiron/utils/datasets.py", line 14, in get_servo_dataset
data = pd.DataFrame.from_csv(filename)
File "/anaconda3/lib/python3.6/site-packages/pandas/core/frame.py", line 1361, in from_csv
infer_datetime_format=infer_datetime_format)
File "/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py", line 709, in parser_f
return _read(filepath_or_buffer, kwds)
File "/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py", line 449, in _read
parser = TextFileReader(filepath_or_buffer, **kwds)
File "/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py", line 818, in init
self._make_engine(self.engine)
File "/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py", line 1049, in _make_engine
self._engine = CParserWrapper(self.f, **self.options)
File "/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py", line 1695, in init
self._reader = parsers.TextReader(src, **kwds)
File "pandas/_libs/parsers.pyx", line 565, in pandas._libs.parsers.TextReader.cinit
pandas.errors.EmptyDataError: No columns to parse from file

How can I train it ?
should I use Joysticks or something ?

Nice work!

Thanks for sharing - great project.
Are you willing to share the raw data you collected?

After reading about the project at

In reality, 20 minutes is no where near enough data. It works great on this particular track with similar lighting conditions but would likely fail if the conditions changed to much.

Your project is inspiring, I'd like to build a car myself. Before doing that I'd like to try out try some different training ideas but need raw data. If you ware willing to share your dataset it would be a real time saver. My guess is others would appreciate it as well.

Thanks,

I have followed the installation instructions but am having a problem during training.

When I run
python ./train.py
the line
network = conv_2d(network, 8, [5, 3], activation='relu')
throws the error
TypeError: variable_scope() got an unexpected keyword argument 'values'

Any thoughts what the problem could be?
Thanks,

python ./train.py
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:108] successfully opened CUDA library libcurand.so locally
[!] Loading dataset...
[!] Finished loading dataset...
Traceback (most recent call last):
  File "./train.py", line 29, in <module>
    servo_model = get_cnn_model(SETTINGS['servo_cnn_name'], SETTINGS['width'], SETTINGS['height'], SETTINGS['depth'])
  File "/data/home/user123/my_tensorflow/suiron/suiron/suiron/core/SuironML.py", line 20, in get_cnn_model
    network = conv_2d(network, 8, [5, 3], activation='relu')
  File "/usr/local/lib/python2.7/dist-packages/tflearn/layers/conv.py", line 72, in conv_2d
    with tf.variable_scope(scope, name, values=[incoming], reuse=reuse) as scope:
  File "/usr/lib/python2.7/contextlib.py", line 84, in helper
    return GeneratorContextManager(func(*args, **kwds))
TypeError: variable_scope() got an unexpected keyword argument 'values'

Does collect.py work for a Raspberry Pi 3? When I execute
python collect.py
the code runs without errors but I notice that the CPU is near zero, output_1.csv does not contain any data while running, after pressing "cntrl-c" output_1.csv only contains the header ",image,servo,motor"

Here is more detail:

1. clone suiron and car-controller
2. Upload car-controller.ino to an Arduino nano
3. Execute python collect.py
4. "Recording data..." and the webcam light turns on, as normal
5. Wait for 10seconds to 1 minute
6. Press cntr-c
7. No data in output_foo.csv

Any thoughts?

So, I updated tensorflow to r0.11, which required upgrading to CUDA 8.0 to be able to use the prebuilt Tensorflow binary for Ubuntu/Linux 64-bit, GPU enabled, Python 2.7.

Tensorflow runs correctly but
python ./suiron/train.py
import cv2
fails with
Traceback (most recent call last): File "./train.py", line 5, in <module> from suiron.utils.datasets import get_servo_dataset File "/data/home/me/my_tensorflow/suiron/suiron/suiron/utils/datasets.py", line 9, in <module> from suiron.utils.img_serializer import deserialize_image File "/data/home/mer/my_tensorflow/suiron/suiron/suiron/utils/img_serializer.py", line 5, in <module> import cv2 ImportError: libcudart.so.7.5: cannot open shared object file: No such file or directory

I spent a lot of time looking for a version of cv built against CUDA 8 but did not find anything.
Any thoughts on the best way to resolve?

Hi great work here.. It seems the link: http://jabelone.com.au/blog/make-autonomous-car-code-included/ I'm get a "not Found" page..
In either case, I wanted to know the order in which to run the python files in the repository.. Thanks