For a project of mine, I am working on Beagle Bone Black(BBB), my objective is to detect fire from real-time video. I tried installing tensor flow. But neither the normal installation nor installing the pre-compiled binary gave positive results. It gives an error saying, 'is not a supported wheel on this platform'. Does BBB support tensorflow? If yes, Could you please help me with this issue?
If not, can anyone of you suggest an object detection API which is supported by BBB?
Thanks in advance.
screenshot of the error
Some people have seen success installing tensorflow in BBB following the guide found on github. You can find it here https://github.com/samjabrahams/tensorflow-on-raspberry-pi/blob/master/GUIDE.md. Hope it helps!
Please note that this should be added as a comment but unfortunately cannot do that (yet).
Related
I want to solve NP-hard combinatorial optimization problem using quantum optimization.In this regard, I am using "classiq" python library, which a high level API for making hardware compatible quantum circuits, with IBMQ backend.
To use "classiq", you have to first do the authentication of your machine (according to the official "classiq" website: https://docs.classiq.io/latest/getting-started/python-sdk/
Unfortunatly, whenever I ran the statement (classiq.authenticate()), I got runtime error as shown in the attached figure (with the full traceback).
enter image description here
Classiq currently requires a license to use. This could be why the authentication fails.
A license can be acquired by contacting:
https://www.classiq.io/contact-us
I think the Classiq API can definitely help you with your use case. But just like mentioned above you should contact Classiq for a license.
I was trying out dlib‘s deep learning-based face detection MMOD, and it worked perfectly fine without any errors. After the weekend, I rerun my google colab, and I get the following error:
RuntimeError: Error while calling cudnnConvolutionBiasActivationForward( context(), &alpha1, descriptor(data), data.device(), (const cudnnFilterDescriptor_t)filter_handle, filters.device(), (const cudnnConvolutionDescriptor_t)conv_handle, (cudnnConvolutionFwdAlgo_t)forward_algo, forward_workspace, forward_workspace_size_in_bytes, &alpha2, out_desc, out, descriptor(biases), biases.device(), identity_activation_descriptor(), out_desc, out) in file /tmp/pip-install-fdw8qrx_/dlib_e3176ea453c4478d8dbecc372b81297e/dlib/cuda/cudnn_dlibapi.cpp:1237. code: 9, reason: CUDNN_STATUS_NOT_SUPPORTED
literally same code previously saved in GitHub, and now in google colab
Any ideas about what could have happened over the weekend, and how to fix it? Thank you!
So after I tried EVERYTHING I could come up with (trying the code on a different machine, on a different platform, check if there were any library updates), I went through my github committed version, and realized, that the dlib library was updated, but not announced anywhere...
So yeah, note for the future self: always include the .version afterimporting the tools, might save DAYS of trying to figure out what on earth happened
I have to monocular USB cameras and I want to use ROS to make it a stereo camera. I am having a hard time finding a ROS package that publishes there 2 images in this format:
/my_stereo/left/camera_info
/my_stereo/left/image_raw
/my_stereo/right/camera_info
/my_stereo/right/image_raw
/my_stereo_both/parameter_descriptions
/my_stereo_both/parameter_updates
/my_stereo_l/parameter_descriptions
/my_stereo_l/parameter_updates
/my_stereo_r/parameter_descriptions
How can I do this? Any help is truly appreciated!
You can use:
http://wiki.ros.org/stereo_image_proc
You can change the publish topic name according to the documentation.
This tutorial provides an example, how exactly to publish the images.
I'm struggling with the disparity topic and posted a question here.
According to the already mentioned tutorial from 2016, the stereo_image_proc node was supposed to do a lot of job, but it looks like that it doesn't exist in ROS2 version. There are two nodes: disparity_node and point_cloud_node.
The blog TensorFlow Lite Now Faster with Mobile GPUs introduce the GPU feature of tensorflow-lite and I have tried the demo followed this tutorial, but I can not find the source code about GPU, so, is it still not open source?
"A full open-source release is planned in later 2019, incorporating the feedback we collect from your experiences."
So, expect the code to be added later this year.
i am doing a project using deep learning and for this i need to take pictures from the kinect and evaluate them. My problem is the resolution of the pictures are 640x860. Due to this i wanted to know if ros freekinect or some library can increase the resolution given a yaml file or something like that? Thank you guys and sorry for the english
Im currently working on a project with Kinect one sensor and the camera resolution is 1920x1080.
if i am not wrong you are currently using the old xbox 360 kinect from what i see here.
I have not heard of libraries that can increase resolutiono yet(this does not mean it do not exist)
But my suggestion is to use the latest hardware found in Microsoft Store here. It cost about $150.
Cheers!