I am using Google Colab to run the BinaryNet Neural Network implemented using theano by the authors of the original paper here: https://github.com/MatthieuCourbariaux/BinaryNet
When I run the following line from /Train-time/mnist.py (line 199):
train_fn = theano.function([input, target, LR], loss, updates=updates)
Colab throws up this error:
You can find the C code in this temporary file:
/tmp/theano_compilation_error_5_e2lq4v library
inux-gnu/bits/libc-header-start.h:33, is not found. library
inux-gnu/7/include-fixed/limits.h:194, is not found. library
inux-gnu/7/include-fixed/syslimits.h:7, is not found. library
inux-gnu/7/include-fixed/limits.h:34, is not found. library
inux-gnu/bits/mathcalls.h:298:1: is not found. library
inux-gnu/bits/mathcalls.h:298:1: is not found. library
inux-gnu/bits/libc-header-start.h:33, is not found. library
inux-gnu/7/include-fixed/limits.h:194, is not found. library
inux-gnu/7/include-fixed/syslimits.h:7, is not found. library
inux-gnu/7/include-fixed/limits.h:34, is not found. library
inux-gnu/bits/mathcalls.h:298:1: is not found. library
inux-gnu/bits/mathcalls.h:298:1: is not found.
Exception: ('The following error happened while compiling the node',
Elemwise{Composite{(i0 * (i1 + (i0 * round3(clip(i2, i3, i4)))) *
i5)}}[(0, 2)](TensorConstant{(1, 1) of 2.0}, TensorConstant{(1, 1) of
-1.0}, Elemwise{Composite{(i0 * (i1 + (i2 * i3 * i4) + i5))}}.0, TensorConstant{(1, 1) of 0}, TensorConstant{(1, 1) of 1},
Elemwise{Composite{Cast{float64}(LT(i0, i1))}}[(0, 0)].0), '\n',
"Compilation failed (return status=1):
/root/.theano/compiledir_Linux-4.19.104+-x86_64-with-Ubuntu-18.04-bionic-x86_64-3.6.9-64/tmp9q80fef3/mod.cpp:932:2:
warning: character constant too long for its type. ['V15_tmp2'] =
round(['V15_tmp1']);. ^~~~~~~~~~.
/root/.theano/compiledir_Linux-4.19.104+-x86_64-with-Ubuntu-18.04-bionic-x86_64-3.6.9-64/tmp9q80fef3/mod.cpp:932:23:
warning: character constant too long for its type. ['V15_tmp2'] =
round(['V15_tmp1']);. ^~~~~~~~~~.
/root/.theano/compiledir_Linux-4.19.104+-x86_64-with-Ubuntu-18.04-bionic-x86_64-3.6.9-64/tmp9q80fef3/mod.cpp:1054:2:
warning: character constant too long for its type. ['V15_tmp2'] =
round(['V15_tmp1']);. ^~~~~~~~~~.
/root/.theano/compiledir_Linux-4.19.104+-x86_64-with-Ubuntu-18.04-bionic-x86_64-3.6.9-64/tmp9q80fef3/mod.cpp:1054:23: warning: character constant too long for its type. ['V15_tmp2'] =
round(['V15_tmp1']);. ^~~~~~~~~~.
/root/.theano/compiledir_Linux-4.19.104+-x86_64-with-Ubuntu-18.04-bionic-x86_64-3.6.9-64/tmp9q80fef3/mod.cpp: In member function ‘in...
I used this to install theano and lasagne:
!pip install --upgrade https://github.com/Theano/Theano/archive/master.zip
!pip install --upgrade https://github.com/Lasagne/Lasagne/archive/master.zip
I am using the exact same code as in the github repo with the only difference being that I used keras to import the mnist dataset instead of pylearn2
Could someone please help me figure out why this is happening? Thank you!
EDIT
I ran my code in python 2.7 and it worked! This question deals with using python 2 in Colab.
Related
python mo_tf.py
--saved_model_dir C:\DATASETS\mask50000\exports\saved_model
--output_dir C:\DATASETS\mask50000
--reverse_input_channels
--tensorflow_custom_operations_config extensions\front\tf\mask_rcnn_support_api_v2.0.json
--tensorflow_object_detection_api_pipeline_config C:\DATASETS\mask50000\exports\pipeline.config
--log_level=DEBUG
I have been trying to convert the model using the above script, but every time I got the error:
"Exception: Exception occurred during running replacer "REPLACEMENT_ID (<class'extensions.front.tf.tensorflow_custom_operations_config_update.TensorflowCustomOperationsConfigUpdate'>)": The function 'update_custom_layer_attributes' must be implemented in the sub-class."
I have exported the graph using exporter_main_v2.py. If more information is needed please inform me.
EDIT:
I was able to convert the model by changing the file mask_rcnn_support_api_v2.4.json.
first change:
"custom_attributes": {
"operation_to_add": "Proposal",
"clip_before_nms": false,
"clip_after_nms": true
}
second change:
"start_points": [
"StatefulPartitionedCall/concat/concat",
"StatefulPartitionedCall/concat_1/concat",
"StatefulPartitionedCall/GridAnchorGenerator/Identity",
"StatefulPartitionedCall/Cast",
"StatefulPartitionedCall/Cast_1",
"StatefulPartitionedCall/Shape"
]
that solved the problme.
OpenVINO 2020.4 is not compatible with TensorFlow 2. Support for TF 2.0 Object Detection API models was fully enabled only in OpenVINO 2021.3.
I’ve successfully converted the model mask_rcnn_inception_resnet_v2_1024x1024_coco17 to IR using the latest OpenVINO release (2021.4.752).
I share the MO conversion command here:
python mo_tf.py --saved_model_dir <model_dir>\saved_model --tensorflow_object_detection_api_pipeline_config <pipeline_dir>\pipeline.config --transformations_config <installed_dir>\extensions\front\tf\mask_rcnn_support_api_v2.0.json"
I'm following the tutorial on using your own template images to do object 3D pose tracking, but I'm trying to get it working on Ubuntu 20.04 with a live webcam stream.
I was able to successfully make my index .pb file with extracted KNIFT features from my custom images.
It seems the next thing to do is load the provided template matching graph (in mediapipe/graphs/template_matching/template_matching_desktop.pbtxt) (replacing the index_proto_filename of the BoxDetectorCalculator with my own index file), and run it on a video input stream to track my custom object.
I was hoping that would be easiest to do in python, but am running into dependency problems.
(I installed mediapipe python with pip3 install mediapipe)
First, I couldn't find how to directly load a .pbtxt file as a graph in the mediapipe python API, but that's ok. I just load the text it contains and use that.
template_matching_graph_filepath=os.path.abspath("~/mediapipe/mediapipe/graphs/template_matching/template_matching_desktop.pbtxt")
graph = mp.CalculatorGraph(graph_config=open(template_matching_graph_filepath).read())
But I get missing calculator targets.
No registered object with name: OpenCvVideoDecoderCalculator; Unable to find Calculator "OpenCvVideoDecoderCalculator"
or
[libprotobuf ERROR external/com_google_protobuf/src/google/protobuf/text_format.cc:309] Error parsing text-format mediapipe.CalculatorGraphConfig: 54:70: Could not find type "type.googleapis.com/mediapipe.TfLiteInferenceCalculatorOptions" stored in google.protobuf.Any.
It seems similar to this troubleshooting case but, since I'm not trying to compile an application, I'm not sure how to link in the missing calculators.
How to I make the mediapipe python API aware of these graphs?
UPDATE:
I made decent progress by adding the graphs that the template_matching depends on to the cc_library deps of the mediapipe/python/BUILD file
cc_library(
name = "builtin_calculators",
deps = [
"//mediapipe/calculators/image:feature_detector_calculator",
"//mediapipe/calculators/image:image_properties_calculator",
"//mediapipe/calculators/video:opencv_video_decoder_calculator",
"//mediapipe/calculators/video:opencv_video_encoder_calculator",
"//mediapipe/calculators/video:box_detector_calculator",
"//mediapipe/calculators/tflite:tflite_inference_calculator",
"//mediapipe/calculators/tflite:tflite_tensors_to_floats_calculator",
"//mediapipe/calculators/util:timed_box_list_id_to_label_calculator",
"//mediapipe/calculators/util:timed_box_list_to_render_data_calculator",
"//mediapipe/calculators/util:landmarks_to_render_data_calculator",
"//mediapipe/calculators/util:annotation_overlay_calculator",
...
I also modified solution_base.py so it knows about BoxDetector's options.
from mediapipe.calculators.video import box_detector_calculator_pb2
...
CALCULATOR_TO_OPTIONS = {
'BoxDetectorCalculator':
box_detector_calculator_pb2
.BoxDetectorCalculatorOptions,
Then I rebuilt and installed mediapipe python from source with:
~/mediapipe$ python3 setup.py install --link-opencv
Then I was able to make my own class derived from SolutionBase
from mediapipe.python.solution_base import SolutionBase
class ObjectTracker(SolutionBase):
"""Process a video stream and output a video with edges of templates highlighted."""
def __init__(self,
object_knift_index_file_path):
super().__init__(binary_graph_path=object_pose_estimation_binary_file_path,
calculator_params={"BoxDetector.index_proto_filename": object_knift_index_file_path},
)
def process(self, image: np.ndarray) -> NamedTuple:
return super().process(input_data={'input_video':image})
ot = ObjectTracker(object_knift_index_file_path="/path/to/my/object_knift_index.pb")
Finally, I process a video frame from a cv2.VideoCapture
cv_video = cv2.VideoCapture(0)
result, frame = cv_video.read()
input_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
res = ot.process(image=input_frame)
So close! But I run into this error which I just don't know what to do with.
/usr/local/lib/python3.8/dist-packages/mediapipe/python/solution_base.py in process(self, input_data)
326 if data.shape[2] != RGB_CHANNELS:
327 raise ValueError('Input image must contain three channel rgb data.')
--> 328 self._graph.add_packet_to_input_stream(
329 stream=stream_name,
330 packet=self._make_packet(input_stream_type,
RuntimeError: Graph has errors:
Calculator::Open() for node "BoxDetector" failed: ; Error while reading file: /usr/local/lib/python3.8/dist-packages/
Looks like CalculatorNode::OpenNode() is trying to open the python API install path as a file. Maybe it has to do with the default_context. I have no idea where to go from here. :(
When to use mxnet-cu101mkl = {version = "==1.5.0",sys_platform = "== 'linux'"}, I get error that I cannot longer import ndarray or nd:
ImportError: cannot import name 'ndarray'
I have no problem with this when using the same code with mxnet-cu101 (no mkl).
Is this just a bug or is this subpackage no longer supported?
I can confirm that mxnet-cu100mkl works fine (version 1.5.0). Very slight CUDA version difference to yours but the package shouldn't change. I think you might be importing a different mxnet here, possibly a folder called mxnet for example. Check the following:
import mxnet as mx
print(mx.__file__)
It should show the path to mxnet within site-packages for you Python environment. e.g.
/home/ec2-user/anaconda3/envs/mxnet_p36/lib/python3.6/site-packages/mxnet/__init__.py
Running this example on ML engine using Cloud composer but am receiving the following error:
AttributeError: 'module' object has no attribute 'estimator'
Even though I am importing import tensorflow as tf and it exits on the following line:
estimator = tf.estimator.Estimator(model_fn = image_classifier,
Runtime version is 1.8 similar to the version using the repo.
t3 = MLEngineTrainingOperator(
task_id='ml_engine_training_op',
project_id=PROJECT_ID,
job_id=job_id,
package_uris=["gs://us-central1-ml/trainer-0.1.tar.gz"],
training_python_module=MODULE_NAME,
training_args=training_args,
region=REGION,
scale_tier='BASIC_GPU',
runtimeVersion = '1.8',
dag=dag
)
Please check the setup.py, make sure you put tensorflow in it as
REQUIRED_PACKAGES = ['tensorflow==1.8.0']. or some other version. Then don't forget to re-generate tar and upload.
Also, in my case, MLEngineTrainingOperator doesn't seem to pick runtime_version or python_version at all into ML Engine.
I used the following code in Pycharm:
import tensorflow as tf
sess = tf.Session()
a = tf.constant(value=5, name='input_a')
b = tf.constant(value=3, name='input_b')
c = tf.multiply(a,b, name='mult_c')
d = tf.add(a,b, name='add_d')
e = tf.add(c,d, name='add_e')
print(sess.run(e))
writer = tf.summary.FileWriter("./tb_graph", sess.graph)
Then, I pasted following line to the Anaconda Prompt:
tensorboard --logdir=="tb_graph"
I tried both with "" and '' as there were proposed: Tensorboard: No graph definition files were found. and it does nothing for me.
I had similar issue. The issue occurred when I specified 'logdir' folder inside single quotes instead of double quotes. Hope this may be helpful to you.
egs: tensorboard --logdir='my_graph' -> Tensorboard didn't detect the graph
tensorboard --logdir="my_graph" -> Tensorboard detected the graph
I checked the code on laptop with Ubuntu 16.04 and another one with Win10, so it probably isn't system-based error.
I also tried adding and removing --host=127.0.0.1 in An Prompt and checking several times both http://localhost:6006/ and http://desktop-.......:6006/.
Still same error:
No graph definition files were found.
To store a graph, create a tf.summary.FileWriter and pass the graph either via the constructor, or by calling its add_graph() method. You may want to check out the graph visualizer tutorial.
....
Please tell me what is wrong in the code/propmp command?
EDIT: On Ubuntu I used the normal terminal, of course.
EDIT2: I used both = and == in command prompt
The answer to my question is:
1) change "./new1_dir" into ".\\new1_dir"
and
2)put full track to file to anaconda propmpt: --logdir="C:\Users\Admin\Documents\PycharmProjects\try_tb\new1_dir"
Thanks #BugKiller for your help!
EDIT: Working only on Windows for me, but still better than nothing
EDIT2: Works on Ubuntu 16.04 too