(Pattern Recognition Letters 2023) PyTorch implementation of "Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformer"

An end-to-end CNN Image Classification Model which identifies the food in your image

Deep learning model that classifies images into 101 food categories using the Food101 dataset.

Deep Food Image Recognition Project

From preprocessing to building a CNN for the Food 101 Dataset

a web App and Mobile app to classify food dishes and then to display recipe of that food

A Food image classification of 101 classes with EfficientNetB0 and streamlit

An example of Chainer software that use Food-101 dataset

Food 101 Classification Model

AI-powered food recognition 🍔🥗 → calorie estimation. ResNet50 fine-tuned on Food-101 (subset) with MLflow tracking, FastAPI backend, and Streamlit UI. Dockerized for local/demo use. Supports both Local (Python) and HTTP API inference modes.

A neural network that can identify 101 different foods from an image. The "Final Model" section contains model weights for EfficientNetB2 + a classifier block that gives a top-1 accuracy of 73.2% and a top-5 accuracy of 91.2%. The models are all trained on the Food101 dataset.

CNN Image Classification Model which identifies the food in your image

Transfer learning and parameter-efficient fine-tuning of CLIP on the Food-101 dataset using Linear Probing and LoRA adapters (TensorFlow + PyTorch).

An implementation of one personal project to gain experience with Generative Adversarial Network models and in particular on Wasserstein GAN with gradient penalty. The final application's purpose is to generate synthetic images given a food category.

A PyTorch-based food classification project comparing EfficientNet-B2 and Vision Transformers (ViT) on the Food101 dataset. Includes performance benchmarks and a live Gradio demo on Hugging Face.

Gives the solution of Food101 Kaggle problem