riya-joshi-401 / D-BREED

A web-app made using flask and Deep learning ( custom CNN model with InceptionResNetV2 ) in python for identifying the breed of the dog from its image.

D-BREED

A web-app made using flask and Deep learning ( custom CNN model with InceptionResNetV2 ) in python for identifying the breed of the dog from its image.
File descriptions:

train.zip - the training set, we are provided the breed for these dogs

test.zip - the test set, we have to predict the probability of each breed for each image

sample_submission.csv - a sample submission file in the correct format

labels.csv - the breeds for the images in the train set

The train folder consists of 10,222 images and test folder consists of 10,357 images.

Each image has a filename that is its unique id.

The dataset comprises of 120 breeds of dogs.

Accuracy achieved after training the model: 91.0959%

Checkout my jupyter notebook