Hello all, sharing one of my experience when i was working on a project to automate the process of extracting meaningful information from Resume and cv. As largest organization receives plenty of resume per day and its become an headache for HR people to went through all the resume ….

so we build an platform which auto collect the useful information from resume and sending it to HR dashboard…

Due to company policy here i am just sharing the demo and path we followed ..and getting the available data on internet and showing result..

Named-entity recognition (NER) (also known as…


For those, who wish to start their journey in object detection…..this blog is for…

This object detection blog involves…

  1. Load pretrained yolo weights
  2. load configuration files and coco data
  3. and made final result using image or video for object detection..

after performing this ,results i got is…


I find an data of amazon food reviews on kaggle …

Data was in raw format ,contains HTML tag and other unnecessary things,first we clean data using functions….

Then,done EDA to visualize the spread of class,as it is two class classification problem….Positive review and Negative review….

Then ,step by step we perform an various algorithm namely KNN,Naive Bayes,Logistic Regression,Decision Tree,GBDT,Random Forest,SVM etc..

find an best model by observing accuracy…

The GitHub link for the amazon Fine Food Reviews Sentiment Analysis is:

https://github.com/akshayashokbhor/sentiment-analysis

Blog By:

Akshay Bhor: Deep learning Engineer

an Data Scientist


Tnsorboard to view .pb file

one of when i solving deep learning problem using tensorflow ,i was using pretrained model in .pb format.

i had to visualize that in order to get the layers inside the structure …

i searched lot on internet .. and i get couple of lines of code…

but,i didnt get the actual code ,how to correctly visualize the pretrained .pb file..

hence writing the complete guide here:

Let’s Start…!!!

  1. you must have .pb file…

if not,then download it..(hahahaha)

2.Open google colab…

and paste the following code

where,just do 1 modification in above code..

instead of “model_filename” ,put the path…


This project is under development ,as I am facing some issues,but i am uploading whatever i done till now…

The vehicle number plate detection consists of 2 major parts…

  1. Detect vehicle number plate using pretrained model like yolo v3..
  2. Convert number on plate to digits using OCR and store it to database

The input image to the model is:


Performance Matrix in Data Science

Why??

we have an Sklearn library in python to compute various performance matrics from data. we can use that library and can compute F1 score,accuracy score ,AUC score etc..

then, why custom implementation from scratch..

simple…to understand the math behind it…Its always welcome when you know the basic mathematics behind some libraries..it will be helpful to us when we are working on complex problems and there we need to create some algorithm from our own when all others failed…

Performance Metrics

There are many performance metrics by which we can evaluate our models performance,they are F1 score,AUC score,accuracy score,confusion metrics…


PM Modi and President Trump

Introduction:

To work our Deep learning model well we need an sufficient data to train it.

but,its not always possible that we have that much of data,sometimes in industry too we get much less data from my personal experience as an deep learning Engineer.

Also,even we have an large dataset ,Deep convolutional neural network models may take days or even weeks to train on very large datasets.

So,we have following questions sometimes in front of us:

  1. I have very low data and my model is not performing well and getting very low accuracy.
  2. Even though i have an enough data…


Smart parking using Artificial Intelligence (AI)

Sometimes ,it is very difficult to find parking to park vehicle.

what we can do ????

think ,think and Think..

we got an solution …Use deep learning to find where we can park our vehicle …

Lets, divide the smart parking problem into bit of sections.

  1. Get the Rough view of the Parking image and fix parking spot as they are continue to be remains constant.
  2. Generate the Training Data to train the model from parking images for classification of empty and occupied space
  3. Run the pre-trained Model on Training Data and obtain accuracy above 95%
  4. Save best model weights


While working with real time data,loading and unloading of data on your system is most curious task.

real time data is in TBs, and if we start downloading it by normal way as we doing always it will take couple of hours ,sometimes days which any industry cant afford to do in todays world.

So,is there any way to do this in fast??

and answer is yes!!!

just follow the steps in order to download the data in few seconds only…

  1. Open your Chrome browser and install CurlWget extension on it

Akshay Bhor ..an Data Scientist

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store