In this post we will see how we can classify handwritten digits using shallow neural network implemented with tf.keras. First, let us import all necessary libraries. After imports, we can use imported module to load digits data. The load_digits() function will just download data and we need to split it into train and test sets. We can also plot some digits to see how they look.

This is a Tensorflow 2.3 implementation of the paper YOLACT: Real-time Instance Segmentation and YOLACT: Better Real-time Instance Segmentation. The paper presents a fully-convolutional model for real- time instance segmentation that achieves 29.8 mAP on MS COCO at 33.5 fps evaluated on a single Titan Xp, which is significantly faster than any previous competitive approach. Unlike original implemetation of YOLACT/YOLACT in which image is resized to 550x550, this repo can handle image of size MxN. For detailed steps to install Tensorflow, follow the Tensorflow installation instructions. The remaining libraries can be installed on Ubuntu 16.04 using via apt-get: The default metrics are based on those used in Pascal VOC evaluation.

Here {PIPELINE_CONFIG_PATH} points to the pipeline config and {MODEL_DIR} points to the directory in which training checkpoints and events will be written. For best results, you should stop the training when the loss is less than 0.1 if possible, else train the model until the loss does not show any significant change for a while. The ideal loss should be below 0.05 (Try to get the loss as low as possible without overfitting the model. Don't go too high on training steps to try and lower the loss if the model has already converged viz. Ideally, we want the loss to be as low as possible but we should be careful so that the model does not over-fit.

In this post we will learn how to make a classification of Moons dataset with a shallow Neural network. The Neural Net we will implemented in TensorFlow 2.0 using Keras API. With the following code we are going to import all libraries that we will need. First, we will generate a random dataset, then we will split it into train and test set. We will also print dimensions of these datasets.

Highlights: In this post we are going to talk more about TensorFlow Wrappers. We are going to compare things before and after TensorFlow 2.0. This post will be the introductory one to the series of posts where we are going to build a wide variety of neural networks. To use TensorFlow in our projects, we need to learn how to program using the TensorFlow API. TensorFlow has multiple APIs that can be used to interact with the library.

Highlights: In this post we are going to talk more about what are TensorFlow data model elements. Those are elements like Constants and Variables. So let's see how we can create an operation like \(c a*b\) and run it with the following lines of code. There are certain programming elements in TensorFlow that are essential for writing any TensorFlow code like Constants and Variables. These data model elements are used to assign and store values.

TensorFlow uses Eager execution, which is a more convenient way to execute the code, and also more "Pythonic". It is a default choice in the latest version TensorFlow 2.0. In TensorFlow 1.x, we first need to write a Python program that constructs a graph for our computation, the program then invokes Session.run(), which hands the graph off for execution to the C runtime. This type of programming is called declarative programming (specification of the computation is separated from the execution of it). So, Sessions provide one way to execute these compositions.

Highlights: In previous post we have talked about TensorFlow Wrappers and there we concluded that tf.keras is the most convenient way to build neural networks. Now we are going to implement one very simple network using this high-level API. Let's start with basic imports. Don't worry if some things are not familiar with all of these libraries, we will use them only for some advanced visualization at the end. The problem we will tackle within this post will be the classification of points in the Circle dataset.

Image Classification is one of the fundamental supervised tasks in the world of machine learning. TensorFlow's new 2.0 version provides a totally new development ecosystem with Eager Execution enabled by default. By me, I assume most TF developers had a little hard time with TF 2.0 as we were habituated to use tf.Session and tf.placeholder that we can't imagine TensorFlow without. Today, we start with simple image classification without using TF Keras, so that we can take a look at the new API changes in TensorFlow 2.0 You can take a look at the Colab notebook for this story. We need to play around with the low-level TF APIs rather than input pipelines.

Image Classification is one of the fundamental supervised tasks in the world of machine learning. TensorFlow's new 2.0 version provides a totally new development ecosystem with Eager Execution enabled by default. By me, I assume most TF developers had a little hard time with TF 2.0 as we were habituated to use tf.Session and tf.placeholder that we can't imagine TensorFlow without. Today, we start with simple image classification without using TF Keras, so that we can take a look at the new API changes in TensorFlow 2.0 You can take a look at the Colab notebook for this story. We need to play around with the low-level TF APIs rather than input pipelines.