Friday, November 17, 2017

TOP STOCKS TO INVEST NOW AND MAKE MONEY

Stock Tips - #BSE #NSE #ShareMarket



With Moody's Uplifted Ratings this is the best time to enter Stock Market.



Look at the recently published Quarterly results , coupled with it the seasonal theme .



Garment Industry will be in limelight and it makes sense to Buy beaten Stocks like INDO COUNT INDUSTRIES LTD. 



#IndoCount can have a target of 180 in next 6 months.



Other theme is LT FOODS ( DAWAAT BASMATI ) as soon Festive season coupled with winter sets in.#LTFoods can have a target of 120 in a year.


#TopStocks

Monday, October 2, 2017

RudraAI VOICE BOT









#VoiceBOT #VoiceAI #VoiceOverShoppingAssistant #VoiceRecognition #MachineLearning #AI #DeepLearning

Complete  Video of Voice over Shopping BOT which can place order over Voice command . 

Sunday, October 1, 2017

VOICE AI BOT


Created a Voice over Shopping BOT which can place order over Voice command .

In the 1st level, Rudra could :

1) Understand voice and take appropriate action e.g.     

 i) Shows the current time when asked the time    

ii) Opens up Google Map when asked for a place ( e.g. Where is Taj Mahal? )

 iii) Opens up the appropriate Shopping Platform ( e.g. #Amazon or #Myntra or #Jabong etc ) when asked to find the item - like find me a red shirt from Jabong .

iv) Can scan images among multiple images in a folder ( think from a UI perspective that you are uploading an image ) and find the appropriate item from the shopping platform.

In the 2nd Level, I had tried to make Rudra reaching towards the Goal like buying me an item . For example, if I say -Buy me a white Shirt from Myntra , it first opens up the appropriate search , then selects the item , then selects the appropriate size , adding it to shopping bag and placing the order  .


Due to security reasons, Myntra couldn't let me move to the final level  after multiple testing , which is understandable but Goal accomplished !


Thursday, September 28, 2017

How to : Your VOICE Based AI

#SpeechRecognition #VoiceBasedAI #DeepLearning #SpeechToText #Abzooba Created a simple Voice based AI Assistant using speech recognition library in python. It does the following : 1) Understands voice 2) Can convert speech to text ( My starting point , as wanted an Assistant who can help me write my stories )

3) Perform simple actions ,Like ?

3A) You ask for the current time and get's it instantly. 3B) Understands the intent or context in the speech and can perform specific action e.g. When I ask Rudra ( Have named my AI after Lord Shiva ) to find the location of a place , it automatically opens Google Map with the particular location , or when I ask to find a similar kind of shirt by providing the picture of a blue shirt , it scans the image and then find similar looking shirt in #Amazon or #Myntra.



Interesting, isn't it?

Pray to Lord Rudra and get started !


Let's look into how I did it.


Some Important Stuff FIRST -

For Speech Recognition, you need Speech Recognition library.

Do a pip install and get it installed.

pyaudio will also be required.

I am using Keras ( which using tensorflow backend) here for further processing .

Google has a great Speech Recognition API. This API converts spoken text (microphone) into written text (Python strings), briefly Speech to Text.

text-to-speech (TTS) system converts normal language text into speech.



Let's Look into the WorkFlow :


Let's see how it works :


A)  I say what TIME is it ....

Good, let's move to more complex stuff !

B)  I say to find me a Location like let's say I ask - Where is Abzooba ?


Automatically opens up Chrome browser with Goggle Map location the particular address.




Great , now let's move to more Complex things .

C) I show an Image to Rudra - I have kept the image in a folder as for now but once you create a simple UI along with it you can just upload the image .


I ask Rudra to search for similar item in #Myntra

Rudra scans the image and then automatically opens up Myntra for the possible choices.







Tuesday, September 26, 2017

Image Classification - Deep Learning

#github project  -  how to loop through a folder containing multiple images and classifying them using Keras and Pre-trained Networks. #tensorflow #keras #CNN #Neuralnet #INCEPTIONV3 #Machinelearning #DeepLearning


ImageClassificationDeepLearning

Here I will show how to loop through a folder containing multiple images and classifying them using Keras and Pre-trained Networks.
#TENSORFLOW #KERAS #NN #NEURALNET #INCEPTIONV3 #MACHINELEARNING #DEEPLEARNING
Our brains make vision seem easy. It doesn't take any effort for humans to tell apart a lion and a jaguar, read a sign, or recognize a human's face. But these are actually hard problems to solve with a computer: they only seem easy because our brains are incredibly good at understanding images.


How it helps ? 

Let’s say you have a folder wherein Multiple images get uploaded – best example will be like OLX or Quickr which are free Buy & Sell websites. Now, you need to determine if any harmful things ( e.g. Gun etc) are being bought and sold .








SEVERAL PRE-TRAINED NETWORKS :
  • VGG16, VGG19, ResNet50, Inception V3, and Xception
State-of-the-art deep learning image classifiers in Keras
Keras ships out-of-the-box with five Convolutional Neural Networks that have been pre-trained on the ImageNet dataset: VGG16 VGG19 ResNet50 Inception V3 Xception
Inception V3
The goal of the inception module is to act as a “multi-level feature extractor” by computing 1×1, 3×3, and 5×5 convolutions within the same module of the network — the output of these filters are then stacked along the channel dimension and before being fed into the next layer in the network. The original incarnation of this architecture was called GoogLeNet, but subsequent manifestations have simply been called Inception vN where N refers to the version number put out by Google.



Saturday, September 23, 2017

Humbled!


Humbled... to be nominated for India-International Achievers’ Awards.


Friday, September 22, 2017

Let’s first write a simple Image Recognition Model using Inception V3 and Keras

Image Recognition

#TENSORFLOW #KERAS #NN #NEURALNET #INCEPTIONV3 #MACHINELEARNING #DEEPLEARNING

Our brains make vision seem easy. It doesn't take any effort for humans to tell apart a lion and a jaguar, read a sign, or recognize a human's face. But these are actually hard problems to solve with a computer: they only seem easy because our brains are incredibly good at understanding images.

SEVERAL PRE-TRAINED NETWORKS :

VGG16, VGG19, ResNet50, Inception V3, and Xception

State-of-the-art deep learning image classifiers in Keras

Keras ships out-of-the-box with five Convolutional Neural Networks that have been pre-trained on the ImageNet dataset:

  1. VGG16
  1. VGG19
  1. ResNet50
  1. Inception V3
  1. Xception



Inception V3


The goal of the inception module is to act as a “multi-level feature extractor” by computing 1×13×3, and 5×5 convolutions within the same module of the network — the output of these filters are then stacked along the channel dimension and before being fed into the next layer in the network.
The original incarnation of this architecture was called GoogLeNet, but subsequent manifestations have simply been called Inception vN where N refers to the version number put out by Google.

LET'S WRITE A NICE LITTLE PROGRAM TO CLASSIFY IMAGES 

What are we going to Detect?
What does this Image say to a Computer?



Let's check it out :

import numpy as np
from keras.preprocessing import image
from keras.applications import inception_v3

# Load pre-trained image recognition model
model = inception_v3.InceptionV3()

# Load the image file and convert it to a numpy array
img = image.load_img('../input/Huggies.jpg', target_size=(299, 299))
input_image = image.img_to_array(img)

# Scale the image so all pixel intensities are between [-1, 1] as the model expects
input_image /= 255.
input_image -= 0.5
input_image *= 2.

# Add a 4th dimension for batch size (as Keras expects)
input_image = np.expand_dims(input_image, axis=0)

# Run the image through the neural network

predictions = model.predict(input_image)

# Convert the predictions into text and print them
predicted_classes = inception_v3.decode_predictions(predictions, top=1)
imagenet_id, name, confidence = predicted_classes[0][0]
#Let's print what the DL Program say
print("This is a {} with {:.4}% confidence!".format(name, confidence * 100))

Output: This is a diaper with 95.24% confidence!

Tuesday, September 19, 2017

HIT PROFIT BY MACHINE LEARNING BASED TRADING

I bought FRESHTROP Fruits at INR 94 on 08th AUGUST 2017 .


WHY ????– a very detailed study on prices across last 10 years or more, using logistic regression and it should that it’s at it lowest trading price.


Today it trades at 143 , today is 19th September , so in around a little more than a month.


Profit per share = 49 Rupees


If you have bought 1000 Shares, ( Investment INR 94000/- Less than a Lakh ) , you have gained around 50,000/- in just 1 month.


Tip – buy now, it will more to 250/- in a period of 1 years or little more .



It’s always make sense to invest with Machine Learning Statistics .


You can follow my blog on investment tips at http://saptak-firsttry.blogspot.in/

#StockTips #MachineLearning #LogisticRegression #AlgorithmicTrading

Followers