FRUIT IDENTIFICATION USING RESENT9 ARCHITECTURE BASED CNN DEEP LEARNING MODEL

Fruits are very good source of Nutrients and Fiber. They are juicy & sweet and also impart Freshness in our diet.
As important it is to eat foods, it is also very important to identify what fruit are we exactly eating, sometimes people with conditions require fruits which are rich in some particular Nutrient or Fiber.

The very aim of this Deep learning Model is to predict the label/name of the given Fruit just by looking at it's Picture.

TABLE OF CONTENTS :-

IMPORTING REQUIRED LIBRARIES
DOWNLOADING THE DATASET FROM KAGGLE
CALCULATING MEAN AND STD DEVIATION OF IMAGES FOR DATA AUGEMENTATION
IMPORTING THE TRAINING AND VALIDATION DATASET USING IMAGEFOLDER METHOD OF PYTORCH AND AUGEMENTING & NORMALISING THE DATA.
CREATING DATALOADERS TO RETREIVE BATCHES OF IMAGES.
SHIFTING THE DATALOADERS ON THE GPU.
EXTENDING THE nn.Module CLASS FOR REQUIRED FUNCTIONS.
DEFINING THE MAIN RESNET9 ARCHITECTURE BASED CNN MODEL.
DEFINING THE MODEL OBJECT AND SHIFTING IT ON THE GPU.
TRAINING THE MODEL AND EVALUATING SIMUNTANEOUSLY.
SAVING THE MODEL USING JOBLIB.
PLOTTING MODEL ACCURACY, LOSS AND LEARNING RATES AGAINST NO OF EPOCHS.
TESTING THE MODEL ON INDIVIDUAL IMAGES.
LOGGING THE HYPERPARAMETERS AND METRICS ON JOVIAN.

!pip install jovian --upgrade --quiet

import jovian

# Execute this to save new versions of the notebook
jovian.commit(project="zerotogans-project")

[jovian] Detected Colab notebook...
[jovian] Please enter your API key ( from https://jovian.ai/ ):
API KEY: ··········
[jovian] Uploading colab notebook to Jovian...
Committed successfully! https://jovian.ai/bhandari2003anurag/zerotogans-project

'https://jovian.ai/bhandari2003anurag/zerotogans-project'

FRUIT IDENTIFICATION USING RESENT9 ARCHITECTURE BASED CNN DEEP LEARNING MODEL

IMPORTING THE REQUIRED LIBRARIES