I'm currently trying to get my SSDLite Network, which I trained with the Tensroflow Object-detection API working, with iOS.
So I'm using the Open Source Code of SSDMobileNet_CoreML.
The Graph allready works with some limitations. For running on iOS I had to extract the FeatureExtractor from my Graph and where unable to keep Preprocessor, Posprocessor and MutlipleGrindAnchorBox, same as they did in SSDMobileNet_CoreML.
Here you can see the Anchors they have used.
So cause my Anchors seem to be a little different I tried to undestand how they got this array.
So I found in an GitHub Issue an explenation, where the User who created the Anchors explains how he got them.
He says:
I just exported them out of the Tensorflow Graph from the import/MultipleGridAnchorGenerator/Identity tensor
I allready found the matching tensor in my Graph but I don't know how to export the Graph and retrive the correct Anchor encoding.
Can sombody explain this to me?
I allready figured it out. A little below quote was a link to a Python Notebook which explains everything in detail.
Related
I try to make one Tutorial work in colab, and faced some problems.
Most of them (somehow :)) solved, but right now i faced with error:
“tensor %s is not an element of this graph” about last layer of my network.
This is the shared link to the notebook: https://colab.research.google.com/drive/1UIDsV2nBwc5jgeNU4WUm_G_Jumr8fRne?usp=sharing 1
Can you, please, help me or give some advise to solve this?
P.S. i’ve changed part of the code in training part to make sure that i can go to interact model.
P.P.S.I've tried some tricks: save and load model, setting default graph and so on (what i've managed to find here), but in the and - i'm failed.
I am trying to use an object detection model, that was created using the TF Object Detection API, in TensorFlow.js.
I converted the model using:
tensorflowjs_converter --input_format=tf_saved_model inference_graph/saved_model inference_graph/web_model
It gets converted without any problems and loads in my javascript code.
Now I am a bit unsure about what my next steps should be.
I have to translate the Python into JavaScript, but certain areas I am unsure about.
With the object detection API in python, there are many steps; (1)preprocessing the image, such as convert to RGB, numpy array reshape, expand dimensions (I have an idea of how I would approach it) and (2) the run inference for single image function, I am not sure how I would go about it in tensorflow.js.
I tried to find some general information about deploying an object detection model in tensorflow.js, but I could not find much, except with pre-trained models.
Any information about this topic would be great!
Thanks!
as mentioned by #edkeveked you will need to perform similar input processing and output processing in JavaScript as is being done in Python. i can't say exactly what you will need to do since i am not familiar with the model. however, you can find an example using a specific object detection model here:
https://github.com/vabarbosa/tfjs-model-playground/blob/master/object-detector/demo/object-detector.js
see also
https://medium.com/codait/bring-machine-learning-to-the-browser-with-tensorflow-js-part-iii-62d2b09b10a3
You would need to replicate the same process in javascript before giving it to the model. In js, the image use by default the RGB channel, so there is no need to make that conversion again.
everyone. Tensorboard is a wonderful tool to visualize learning process, but it has some inconvenience for me. For some reason, sometimes I want to remove part of learning curve (like erase scalars after X-th step). However, all scalars are put together in a single "events.*" file, plus Tensorboard only provides high-level api (only "adding" but no "removing") to the best of my knowledge. Does anyone have some ideas about this? Thanks!
You can view the contents of a checkpoint file using print_tensors_in_checkpoint_file(),
from tensorflow.python.tools.inspect_checkpoint import print_tensors_in_checkpoint_file
print_tensors_in_checkpoint_file(file_name="<your_path_here>/model.ckpt-<whatever_step>", tensor_name='', all_tensors=True)
I'm putting my first steps in Machine Learning, I went through many TensorFlow.js tutorials already and I'm trying to achieve this: "Realtime Single Object Tracking/Detection"
Something like this -> input: webcam/video -> output: object bounding box
I know there are SSD and YOLO, and other libraries to predict & locate the objects. But the predicted time is very slow (in browser), I guessed it's because the Neural Network have to predict between so many objects.
https://github.com/ModelDepot/tfjs-yolo-tiny
https://github.com/tensorflow/models/tree/master/research/object_detection
What if I just want to track a single object? Would it be possible? Will the performance be better? Where should I start?
I've been thinking about extract the pre-trained class (object) from a SavedModel, then start training more from it. But there don't seems to be any instructions around Google.
I found some fantastic code by IBM, which I used in the video in this tweet: https://twitter.com/GantLaborde/status/1125735283343921152?s=20
I extracted that code to make a ReactJS component for detecting Rock/Paper/Scissors here: https://github.com/GantMan/rps_tfjs_demo/blob/master/src/AdvancedModel.js
If you'd like to play with the demo, it's at the bottom of this page: https://rps-tfjs.netlify.com/
All of this is open source and seems to work perfectly fast for detecting a single object in realtime.
I'm trying to send image input over http to classify using tensorflow. I have looked in detail in the c++ code for https://www.tensorflow.org/versions/r0.9/tutorials/image_recognition/index.html
I have implemented the inception-v3 example model using C++ API. It takes image input in the following form:
bazel-bin/tensorflow/examples/label_image/label_image --image=my_image.png
However, I want to add the case of:
bazel-bin/tensorflow/examples/label_image/label_image --image=http://www.somewebsite.com/my_image.png
This is due to the fact that it only accepts local image files. I want to add the functionality to take file pointers from online images and classify it in memory. I'm currently working on this, but so far no luck. Can anyone offer some insight how I would go about implementing this?