I am trying to debug this project : https://github.com/VisualComputingInstitute/TrackR-CNN
This is a MaskRCNN based project and I want to visualize the data flow among various functions in network/FasterRCNN.py(https://github.com/VisualComputingInstitute/TrackR-CNN/blob/master/network/FasterRCNN.py)
mainly rpn_head(), fastrcnn_head(). I tried it with py_func and pdb but was not successful. SEssion.run() is created inside core/Engine.py(https://github.com/VisualComputingInstitute/TrackR-CNN/blob/master/core/Engine.py).
Is there any way to see the image manipulation during the training(i.e. rpn values, reid_dim, etc)?
Thanks.
Related
We are investigating transitioning our ML pipelines from a set of manual steps into a TFX pipeline.
I do however have some questions for which I would like to have some additional insights.
We typically perform the following steps (for an image classification task):
Load image data and meta-data
Filter out ‘bad’ data based on meta-data
Determine image based statistics (classic image processing in Python):
Image level characteristics
Image region characteristics
(region is determined based on a fine-tuned EfficientDet model)
Filter out ‘bad’ data based on image statistics
Generate TFRecords from this image and meta-data
Oversample certain TFRecords for class balancing (using tf.data)
Train an image classifier
…
Now, I’m trying to map this onto the typical example TFX pipeline.
This however raises a number of questions:
I see two options:
ExampleGen uses a CSV file containing pointers to the image to be loaded and the meta-data to be loaded (above step ‘1’). However:
If this CSV file contains a path to an image file, can ExampleGen then load the image data and add this to its output?
Is the output of ExampleGen a streaming output, or a dump of all example data?
ExampleGen has TFRecords as input (output of above step ‘5’)
-> This implies that we would still need to implement steps 1-5 outside of TFX… Which would decrease the value for TFX for us…
Could you please advice what would be the best way forward?
Can StatisticsGen also generate statistics on a per-example base (for example some image (region) characteristics based on classic image processing)? Or should this be implemented in ExampleGen? Or…?
Can the calculated statistics be cached using the metadata store? If yes, is there an example of this available?
Calculating image based characteristics using classic image processing is slow. If new data becomes available, triggering the TFX input component to be executed, ideally already calculated statistics should be loaded from the cache.
Is it correct that ExampleValidator may reject some examples (e.g. missing data, outliers, …)?
How can class balancing at the network input side (not via the loss function) be achieved in this setup (normally we do this by oversampling our TFRecords using tf.data)?
If this is done at the ExampleGen level, then the ExampleValidator may still reject some examples potentially unbalancing the data again.
This may not seem like a big issue for large data ML tasks, but it becomes crucial for small data ML tasks (as typically is the case in a healthcare setting).
So I would expect a TFX component for this before the Transform component, but this block should then have access to all data, not in a streaming way (see my earlier question on ExampleGen output)…
Thank you for your insights.
I'll try to address most questions with my experience with tfx.
I have a dataflow job that I run to pre-process my images, labels, features, etc and turn all that into tfrecords. That lives outside of tfx and is ran only when there is data refreshes.
You can do the same, here is a very simple code snippet that i use to resize all my images and create simple features.
try:
image = tf.io.decode_jpeg(image_string)
image = tf.image.resize(image,[image_resize_size,image_resize_size])
image = tf.image.convert_image_dtype(image/255.0, dtype=tf.uint8)
image_shape = image.shape
image = tf.io.encode_jpeg(image,quality=100)
feature = {
'height': _int64_feature(image_shape[0]),
'width' : _int64_feature(image_shape[1]),
'depth' : _int64_feature(image_shape[2]),
'label' : _int64_feature(labels_to_int(element[2].decode())),
'image_raw' : _bytes_feature(image.numpy())
}
tf_example = tf.train.Example(features=tf.train.Features(feature=feature))
except:
print('image could not be decoded')
return None
Once I have the data in tfrecord format, I use the ImportExampleGen component to load the data into my tfx pipeline. This is followed by StatisticsGen which will compute statistics on the features.
When running all of this in the cloud, it is using dataflow under the covers in batch mode.
Your metadata store only caches pipeline metadata, but your data is cached in a gcs bucket and metadata store knows it. So when you re-run your pipeline, if you have caching set to True, your ImportExampleGen, StatisticsGen, SchemaGen, Transform will not be reran if the data hasn't changed. This has huge benefits in time and costs.
ExampleValidator outputs an artifact to let you know what data anomalies are in your data. I created a custom component that intakes the examplevalidator artifact and if my data doesn't meet certain criteria, I kill the pipeline by throwing an error in this component. I wish there was a component that can just stop the pipeline, but I haven't found one, so my work around was to throw an error which stops the pipeline from progressing further.
Usually when I create a tfx pipeline, it is done to automate the machine learning process. At this point we have already done class balancing, feature selection, etc. Since that falls more under the pre-processing stage.
I guess you could technically create a custom component that takes a StatisticsGen artifact, parses it and tries to do some class balancing and creates a new dataset with balances classes. But honestly, I think is better to do it at the preprocessing stage.
Data augmentation can easily be achieved using ad hoc modules in e.g. TensorFlow. This works perfectly for classification problems, however when the objective of the network is the prediction of a geometrical feature, e.g. a landmark, a problem arises. As the image is modified, e.g. flipped, or distorted, the corresponding labels also need to be adapted.
1 - Is there any tool to do this? I am sure that this is a common problem.
2 - Would it be useful to create a data augmentation script for neural networks that predict geometrical features?
I want to understand if I need to code all of this by myself or if I am missing something that already exists. If I need to do it and it could be useful I would just create an open source thing.
You can use imgaug library https://github.com/aleju/imgaug
An example of augmentation for key points using imgaug you can find here https://github.com/aleju/imgaug#example-augment-images-and-keypoints
Is there a low-level API to write custom things into the tensorboard input directory?
For instance, this would enable writing summaries into the tensorboard directory without writing them from a tensorflow session, but from a custom executable.
As far as I can see, all the tensorboard inputs are inside a single append-only file where the structure of the file is not declared ahead (ie how many items we expects, what is their type, etc).
And each summary proto is sequentially written to this file through this class : https://github.com/tensorflow/tensorflow/blob/49c20c5814dd80f81ced493d362d374be9ab0b3e/tensorflow/core/lib/io/record_writer.cc
Was it ever attempted to manually create tensorboard input?
Is the format explicitely documented or do I have to reverse-engineer it?
thanks!
The library tensorboardX provides this functionality. It was written by a pytorch user who wanted to use tensorboard, but it doesn't depend on pytorch in any way.
You can install it with pip install tensorboardx.
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?