Downloads · 30 days
33
3% of all-time downloads
video-vision-transformer
keras-io/video-vision-transformer
video-vision-transformer is a machine learning model from keras-io. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for tf-keras. The card lists the license as apache-2.0.
This repo contains the model to this Keras example on Video Vision Transformer.
All-time downloads
959
Public
Repo size
74.3 MB
Likes
11
Trending 1
Repo makeup
Click a slice to open those files.
.data-00000-of-000016.7 MB · 74%
At a glance
- Library
- tf-keras
- License
- apache-2.0
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jul 5, 2024
- SHA
- 78ed3e37
Model card
From the Hugging Face model README
Keras Implementation of Video Vision Transformer on medmnist
This repo contains the model to this Keras example on Video Vision Transformer.
Background Information
This example implements ViViT: A Video Vision Transformer by Arnab et al., a pure Transformer-based model for video classification. The authors propose a novel embedding scheme and a number of Transformer variants to model video clips.
Datasets
We use the MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification dataset.
Training Parameters
# DATA
DATASET_NAME = "organmnist3d"
BATCH_SIZE = 32
AUTO = tf.data.AUTOTUNE
INPUT_SHAPE = (28, 28, 28, 1)
NUM_CLASSES = 11
# OPTIMIZER
LEARNING_RATE = 1e-4
WEIGHT_DECAY = 1e-5
# TRAINING
EPOCHS = 80
# TUBELET EMBEDDING
PATCH_SIZE = (8, 8, 8)
NUM_PATCHES = (INPUT_SHAPE[0] // PATCH_SIZE[0]) ** 2
# ViViT ARCHITECTURE
LAYER_NORM_EPS = 1e-6
PROJECTION_DIM = 128
NUM_HEADS = 8
NUM_LAYERS = 8
- Library
- tf-keras
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Jul 5, 2024