Brandon Victor Multihuntr

A deep learning researcher with an interest in algorithms. I never get as much done as I'd hoped.

8 followers · 5 following

La Trobe University

View GitHub Profile

Recently created

Least recently created

Recently updated

Least recently updated

Multihuntr / minimal_nvvl_tests.py

Created June 11, 2018 03:45

Minimal examples of using NVIDIA/nvvl

	# Simplest case (note: VideoDataset.__get__ puts frames on CPU)
	import nvvl
	d = nvvl.VideoDataset(['prepared.mp4'], 3)
	fr = d[0]
	print(type(fr))
	print(fr.shape)

	# Custom processing (note: VideoDataset.__get__ puts frames on CPU)
	import nvvl
	d = nvvl.VideoDataset(['prepared.mp4'], 3, processing={'a': nvvl.ProcessDesc()})

Multihuntr / accumulate_grads_min.py

Created January 23, 2018 07:21

A minimal example of how you can accumulate gradients across batches, allowing you to train using much larger batch sizes than can fit in memory at the cost of speed.

	import numpy as np
	import tensorflow as tf
	import sys

	from tensorflow.examples.tutorials.mnist import input_data

	n_pseudo_batches = int(sys.argv[1]) if len(sys.argv) > 1 else 128
	actual_batch_size = int(sys.argv[2]) if len(sys.argv) > 2 else 32
	iterations = int(sys.argv[3]) if len(sys.argv) > 3 else 10

Multihuntr / accumulate_grads.py

Last active August 10, 2018 08:25

Accumulating gradients to reduce memory requirement per forward pass (using MNIST)

	import numpy as np
	import tensorflow as tf

	from tensorflow.examples.tutorials.mnist import input_data

	def simple_model(input):
	# This ensures that the model will always be instantiated the same, for comparison.
	hidden_initializer = tf.constant_initializer(np.random.uniform(-0.025, 0.025, size=[784,100]))
	hidden = tf.layers.dense(input, 100, kernel_initializer=hidden_initializer)
	out_initializer = tf.constant_initializer(np.random.uniform(-0.025, 0.025, size=[100,10]))

Multihuntr / random_queue.py

Created October 20, 2017 07:55

Blocking Thread-safe Random Queue

	import queue
	import random

	class RandomQueue(queue.Queue):
	def _put(self, item):
	n = len(self.queue)
	i = random.randint(0, n)
	self.queue.insert(i, item)

NewerOlder