Skip to content

Instantly share code, notes, and snippets.

View meet-minimalist's full-sized avatar
😎
Deep Learning Practitioner

Meet Patel meet-minimalist

😎
Deep Learning Practitioner
  • India
View GitHub Profile
@gyglim
gyglim / tensorboard_logging.py
Last active August 23, 2023 21:29
Logging to tensorboard without tensorflow operations. Uses manually generated summaries instead of summary ops
"""Simple example on how to log scalars and images to tensorboard without tensor ops.
License: BSD License 2.0
"""
__author__ = "Michael Gygli"
import tensorflow as tf
from StringIO import StringIO
import matplotlib.pyplot as plt
import numpy as np
#! /usr/bin/env python3
"""Run from root directory of repo https://github.com/lengstrom/fast-style-transfer to
create a .pb for use with OpenVINO.
"""
import sys
sys.path.insert(0, 'src')
import transform
import argparse
import tensorflow as tf
import os
@josepdecid
josepdecid / ColabReconnect.js
Last active November 2, 2023 10:06
Colab Reconnect
// Interval time to check if runtime is disconnected
interval = 1000 * 60;
// Busy/Reconnect button top-right
reloadButton = document.querySelector('#connect > paper-button > span')
setInterval(() => {
if (reloadButton.innerText == 'Reconnect') {
reloadButton.click();
console.log('Restarting');
@sayakpaul
sayakpaul / rand_augment_tfrecords.py
Last active April 30, 2023 07:03
Example of incorporating RandAugment in a tf.data pipeline for image classification.
from imgaug import augmenters as iaa
import imgaug as ia
ia.seed(4)
import tensorflow as tf
tf.random.set_seed(666)
aug = iaa.RandAugment(n=2, m=9)
BATCH_SIZE = 224