Skip to content

Instantly share code, notes, and snippets.

View sayakpaul's full-sized avatar
:octocat:
Learn, unlearn and relearn.

Sayak Paul sayakpaul

:octocat:
Learn, unlearn and relearn.
View GitHub Profile

Machine information

Parameter Value
OS Ubuntu 20.04.5
Python 3.8.10
CUDA 11.8
TensorFlow 2.10.1
TensorRT 8.5.1
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
import tensorflow as tf
from tensorflow.keras import layers
model = tf.keras.Sequential([
layers.Conv2D(32, kernel_size=(3, 3),activation='relu',
layers.MaxPool2D((2, 2)),
layers.Conv2D(64,kernel_size=(3, 3), activation='relu'),
layers.MaxPool2D((2, 2)),
layers.Dropout(0.2),
layers.GlobalAveragePooling2D(),
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@sayakpaul
sayakpaul / feather-tf-poc-bytes.ipynb
Last active August 25, 2022 05:10
Demonstrates the compatibility between Feather and TensorFlow with a real dataset.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@sayakpaul
sayakpaul / setup_big_vision_for_imagenet1k_training.md
Last active May 11, 2022 07:40
Notes for setting up a TPU v3-8 VM with `big_vision` for training on ImageNet-1k

Useful variables

export NAME="big_vision_exp"
export ZONE="us-central1-a"
export REGION="us-central1"
export GS_BUCKET_NAME="big_vision_exp"
Work Details
Augmenting convnets with aggregated attention Tutorial by Aritra
Train a Vision Transformer on small datasets Tutorial by Aritra
MobileViT Tutorial by Sayak
Compact Convolutional Transformers Tutorial by Sayak
Data efficient image transformers TF implementation, TF pre-trained models, tutorial by Sayak
Class attention image transformers TF implementation, TF pre-trained models by Sayak
Masked Autoencoders TF implementation, tutorial by Aritra and Sayak,
Contribution to Hugging Face Transformers by Aritra and Sayak
Probing the representation of ViTs