I am using Microsoft custom vision service in object detection to extract the wanted objects. And I would like to make a regression test to compare the results. However, I cannot find a place to export the training picture with the bounding box that user defined by GUI.
The model training is done within the custom vision platform provided by Microsoft (https://www.customvision.ai/). Within this platform we can add the images and then tag the objects. I have tried to export the model, but I am not sure where to find the info of training pictures along with their tag(s) and bounding box(es).
I expect that in this platform, user can export the not only the trained model but also the training data (images with tags and bounding boxes.) But I was not able to find them.
All the data that you are looking for is available through Custom Vision Training API. Currently the latest API is v3.0, its portal is here.
More in details, GetTaggedImages method will give you the associations of images and regions bounding box
Sample result of this method with one of my demos:
With these details, you will be able to get the image and place the boundingBox that was used for training.
Please see the following link for export your model. Custom Vision Service exports compact domains. The models generated by compact domains are optimized for the constraints of real-time classification on mobile devices. If the user wants to export the user training data from the custom vision please see the following link.
Related
I am playing with Tensorflow Object Detection API and training the Faster R-CNN network on my own dataset. I am checking the progress of learning at Tensorbord. All metrics are there, but is there a way to have both loss plots, for training and validation data, on one graph? Or do I have to dive into TOD Api code and modify it? I would like to avoid the second because during every update of the API I will have to keep in mind that some of the code is changed locally.
The underlying data for the plots is saved under different tag names (loss vs loss_1). I believe TensorBoard does not natively support displaying different tags in one plot. There might be third-party extensions to do this.
If different models used the same tag, the graphs would be combined by default (see: Plot multiple graphs in one plot using Tensorboard).
I'm actualy new in Machine Learning, but this theme is vary interesting for me, so Im using TensorFlow to classify some images from MNIST datasets...I run this code on Compute Engine(VM) at Google Cloud, because my computer is to weak for this. And the code actualy run well, but the problam is that when I each time enter to my VM and run the same code I need to wait while my model is training on CNN, and after I can make some tests or experiment with my data to plot or import some external images to impruve my accuracy etc.
Is There is some way to save my result of trainin model just once, some where, that when I will decide for example to enter to the same VM tomorrow...and dont wait anymore while my model is training. Is that possible to do this ?
Or there is maybe some another way to do something similar ?
You can save a trained model in TensorFlow and then use it later by loading it; that way you only have to train your model once, and use it as many times as you want. To do that, you can follow the TensorFlow documentation regarding that topic, where you can find information on how to save and load the model. In short, you will have to use the SavedModelBuilder class to define the type and location of your saved model, and then add the MetaGraphs and variables you want to save. Loading the saved model for posterior usage is even easier, as you will only have to run a command pointing to the location of the file in which the model was exported.
On the other hand, I would strongly recommend you to change your working environment in such a way that it can be more profitable for you. In Google Cloud you have the Cloud ML Engine service, which might be good for the type of work you are developing. It allows you to train your models and perform predictions without the need of an instance running all the required software. I happen to have worked a little bit with TensorFlow recently, and at first I was also working with a virtualized instance, but after following some tutorials I was able to save some money by migrating my work to ML Engine, as you are only charged for the usage. If you are using your VM only with that purpose, take a look at it.
You can of course consult all the available documentation, but as a first quickstart, if you are interested in ML Engine, I recommend you to have a look at how to train your models and how to get your predictions.
I am building a translator machine using microsoft translator API and HUB. I am trying to build a Japanese to English translator, so I trained the system from japanese to english. I have trained some documents into my translator system. However, i got some confusion about the MT and reference.
My question is, why API translation from microsoft is different either with MT or Reference?
I thought the API provided from microsoft equals to MT which will become Reference after the training? Could you give me some idea?
The Ref: text that you see is part of the training/test data has been provided. The MT text that you see is the translation of the same text that has been produced from the trained translation model.
This is immediately after you have trained a system.
Once you have deployed a trained system, the MT text that you see will be the result of a translate API operation.
The current API translation that you see may be different because of a differently trained model being present there.
I am very new to CNTK.
I wanted to train a set of images (to detect objects like alcohol glasses/bottles) using CNTK - ResNet/Fast-R CNN.
I am trying to follow below documentation from GitHub; However, it does not appear to be a straight forward procedure. https://github.com/Microsoft/CNTK/wiki/Object-Detection-using-Fast-R-CNN
I cannot find proper documentation to generate ROI's for the images with different sizes and shapes. And how to create object labels based on the trained models? Can someone point out to a proper documentation or training link using which I can work on the cntk model? Please see the attached image in which I was able to load a sample image with default ROI's in the script. How do I properly set the size and label the object in the image ? Thanks in advance!
sample image loaded for training
Not sure what you mean by proper documentation. This is an implementation of the paper (https://arxiv.org/pdf/1504.08083.pdf). Looks like you are trying to generate ROI's. Can you look through the helper functions as documented at the site to parse what you might need:
To run the toy example, make sure that in PARAMETERS.py the datasetName is set to "grocery".
Run A1_GenerateInputROIs.py to generate the input ROIs for training and testing.
Run A2_RunCntk_py3.py to train a Fast R-CNN model using the CNTK Python API and compute test results.
The algo will work on several candidate regions and then generate outputs: one for the classes of objects and another one that generates the bounding boxes for the objects belonging to those classes. Please refer to the code for getting the details of the implementation.
Can someone point out to a proper documentation or training link using which I can work on the cntk model?
You can take a look at my repository on GitHub.
It will guide you through all the steps required to train your own model for object detection and classification with CNTK.
But in short the proper steps should look something like this:
Setup environment
Prepare data
Tag images (ground truth)
Download pretrained model and create mappings for your custom dataset
Run training
Evaluate the model on test set
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?