Learn practical skills, build real-world projects, and advance your career
Updated 3 years ago
Image Classifier Using ResNet9 Architecture
We are going to train a deep learning neural network to classify the images of various food items.The dataset used for training the model is the Food-101 dataset which can be downloaded from https://s3.amazonaws.com/fast-ai-imageclas/food-101.tgz.
The dataset has 101 food categories, with 101,000 images; 250 test images and 750 training images per class. The training images were not cleaned. All images were rescaled to have a maximum side length of 512 pixels.Hence while applying tranforms we would be reshaping the size of each image to 150 pixels by 150 pixels.
As a starting step,let's import Jovian python library and commit our code to our respective jovian account.
!pip install jovian --upgrade --quiet
project_name='my-course-prj'
jovian.commit(project=project_name)
[jovian] Detected Colab notebook...
[jovian] Uploading colab notebook to Jovian...
[jovian] Capturing environment..
[jovian] Attaching records (metrics, hyperparameters, dataset etc.)
[jovian] Committed successfully! https://jovian.ai/abdevilliers/my-course-prj