Pandas DataFrame
az network nsg rule list
TensorFlow take
Matplotlib | plt.scatter()
Numpy arange
TensorFlow batch()
Python yield
from_tensor_slices()
Python zip()
from_tensors
Pandas dropna
findall() vs finditer()
Python re.findall()
TensorFlow tf.math.top_k
az network vnet
Python enumerate
terraform-install
rust read file
az vm list-ip-addresses
pd.concat
df.filter
df.pivot
ELU
az vm create
Pandas s.str.upper()
Pandas df.apply()
storage.Client()
compile rust
batch_flatten
pillow
Jenkins installation
Docker installation
Pandas iloc
TensorFlow Datasets
functional model
softplus
getattr
softmax
TextLineDataset
tanh
lambda requests
pd.melt
logging
install rust
BinaryCrossEntropy
Docker-Installation
list_physical_devices
rust cargo
flatten()
Boston-Dataset
nodejs installation
ReLU
Crossentropy
flat_map
Pandas | df.fillna()
KDS
Python unpack operator
test command
String Operators
Pandas s.str.lower()
sigmoid
stack
cuda-version
__slots__
tf.keras
__str__
from_tensor_slices
total_ordering
az network nsg list
tf.keras.utils
Dataset repeat
tf.random.uniform()
soup.find()
TensorFlow dataset.map
Numpy np.power()
Python finditer()
tf.keras.losses.cosine_similarity

embeddings in machine learning are used to represent text with embedding vectors. TensorFlow hub module provides several pre trained text-embeddings models to convert sentence into embedding vectors.

Code snippets for this post is written with TensorFlow2.0. This post is intended to provide information on Tensorflow canned estimators, using this in live trading is not advised

tf.reduce_sum in TensorFlow reduces input_tensor along the dimensions given in axis. If axis is None, all dimensions are reduced, and a tensor with a single element is returned. Below are the example for tf.reduce_sum in TensorFlow

This post describes how to extract text form images using keras-ocr in Python.

This post describes how to use text_dataset_from_directory in TensorFlow.

tf.keras.losses.cosine_similarity function in tensorflow computes the cosine similarity between labels and predictions.

Part 1 of multi part series for deploying TensorFlow pre trained model on Flask.

TensorFlow provides implementation of Sequential model with tk.keras.Sequential API. Sequential model is used when each layer has only one input tensor and one output tensor.

The convolution layer uses filters that perform convolution operations as it is scanning the input I with respect to its dimensions.TensorFlow provides tf.keras.layers.Conv2D class for implementing 2D convolution layer.

In this tutorial we will see how to use MobileNetV2 pre trained model for image classification. MobileNetV2 is pre-trained on the ImageNet dataset. MobileNetV2 model is available with tf.keras api.

Tokenization is an important step of pre-processing the data,Tokenizer class in Keras turns text into a sequence of integers.

Overview of TensorFlow Datasets, a collection of ready-to-use datasets. Loading datasets with TensorFlow Datsets

This tutorial explains how to get weights of dense layers in keras Sequential model.

In the Part 2 of this series we have set flask application, in this Part 3 we will integrate TensorFlow Model with our Flask application.

This post describes How to create tensors in TensorFlow

This post describes how to deploy a TensorFlow model using Flask.

This post describes how to use EarlyStopping callback in TensorFlow with Keras API.

This post describes how to create regression model in TensorFlow

This posts explains how to use GlobalMaxPooling2D layer with TensorFlow.

Feature extraction in quite common while using transfer learning in ML.In this tutorial you will learn how to extract features from tf.keras.Sequential model.

In TensorFlow Categorical values can be transformed to one-hot-encoded vectors by using tf.feature_column.categorical_column_with_vocabulary_list function with tf.feature_column.indicator_column function.

ELMo is a pre-trained model provided by google for creating word embeddings. It can be used directly from TensorFlow hub.

GloVe is an unsupervised learning algorithm for obtaining vector representations for words.

Installation of TensorFlow CPU can be done in 3 simple steps

TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools to build and deploy ML powered applications.

TensorFlow provides tf.io and tf.image modules for reading and processing the images.

This post describes how to use tf.convert_to_tensor method to covert Python objects to tensors.

This post describes how to calculate euclidean norm in TensorFlow.

This post describes how to use TensorBoard in TensorFlow.

This post describes how to install Latest TensorFlow Version using conda and PIP.

TensorFlow tf.GradientTape() records operations for automatic differentiation. Below are the code snippet for calculating gradient of loss function. This post uses some other TensorFlow apis like tf.reduce_sum, tf.constant and tf.variable as well.

stack() method of TensorFlow creates a stacked tensor whose rank is one higher than each tensors given in "value" parameter.