search

sandptel / captcha_iitkgp

This repository aims to provide a deployable model to solve the captchas given in the erp website.
MIT License
9 stars 4 forks source link

Improve the Readme file. #1

Open sandptel opened 1 year ago

sandptel commented 1 year ago

Change the old readme file to a better visual.

Veerhan-glitch commented 1 year ago

hey can u assign it to me? (see ALG for a reference of my work)

sandptel commented 1 year ago

hey can u assign it to me? (see ALG for a reference of my work)

Ok sure.

Veerhan-glitch commented 1 year ago

CRNN OCR

Open In Colab Kaggle Dataset

This repository provides you with a deployable model to solve captchas which contains characters with random alphanumeric character which has been strikethrough vertically and/or horizontally.

The tool to scrap these images from the website is available on google colab

Check out my LinkedIn post for the description, use case, and other relevant information.

Table of Contents

Type of solvable captchas:

Image Alt

How to use

Make sure you have a Google account and are signed in to access and run the notebook.

  1. Go to Colab Notebook

  2. Add your folder path to captchasolve function and get a list of strings with predicted texts.

  3. Follow the instructions provided in the notebook to run and interact with the project.

Accuracy

Kaggle Dataset Open In Colab

  1. Test the accuracy of model using the notebooks given above on testdataset.

add it in the first line

Veerhan-glitch commented 1 year ago

above is what i have done till no, i am not making a pr as i am not done yet as i needed the code to run for a better understanding which is not happening,

it is giving me some errors so can u pls help me debug them?

in from tensorflow.keras.models import Sequential, save_model, load_model model = load_model("/content/kaggle/working", compile = True)

it gives /content/kaggle/working is not found

(also should i also do issue #8 as i am already doing it to run the code)

sandptel commented 1 year ago

/content/kaggle/working is the part where it fetches the dataset from the kaggle server. You either run the notebook already provided in kaggle or simply change the location to " /content/kaggle/working " to the location of the downloaded dataset on your server or pc.