emrectn’s gists

emrectn / gist:7df7c536774a953f1f548548d6aa2321

Created March 7, 2022 11:57

monitor_docker_stats

	#!/bin/bash

	TODAY=$(date +"%Y-%m-%d_%H_%M_%S")
	DATE=`date`

	display_help() {
	echo
	echo " -h, --help Help"
	echo " -o, --output_dir Set on which display to host on "
	echo " -c --container_name Watch Specific container name, if you don't use it it will track all containers"

emrectn / download_file_from_gdrive.sh

Created July 22, 2020 08:20

	#!/bin/bash
	fileid="$1"
	filename="$2"
	curl -c ./cookie -s -L "https://drive.google.com/uc?export=download&id=${fileid}" > /dev/null
	curl -Lb ./cookie "https://drive.google.com/uc?export=download&confirm=`awk '/download/ {print $NF}' ./cookie`&id=${fileid}" -o ${filename}

	remove cookie

emrectn / run_generic.py

Created April 5, 2020 16:10

	best, best_loss = run_style_transfer(content_path,
	style_path,
	verbose=True,
	show_intermediates=True)

emrectn / get_feature_representations.py

Created April 5, 2020 16:06

	def get_feature_representations(model, content_path, style_path):
	"""Helper function to compute our content and style feature representations.

	This function will simply load and preprocess both the content and style
	images from their path. Then it will feed them through the network to obtain
	the outputs of the intermediate layers.

	Arguments:
	model: The model that we are using.
	content_path: The path to the content image.

emrectn / content_loss.py

Created April 5, 2020 13:02

	def get_content_loss(base_content, target):
	return tf.reduce_mean(tf.square(base_content - target))

emrectn / run_style_transfer.py

Created April 5, 2020 12:53

	def run_style_transfer(content_path,
	style_path,
	num_iterations=1000,
	content_weight=1e3,
	style_weight = 1e-2):
	display_num = 100
	# We don't need to (or want to) train any layers of our model, so we set their trainability
	# to false.
	model = get_model()
	for layer in model.layers:

emrectn / compute_grads.py

Created April 5, 2020 12:53

	def compute_grads(cfg):
	with tf.GradientTape() as tape:
	all_loss = compute_loss(**cfg)
	# Compute gradients wrt input image
	total_loss = all_loss[0]
	return tape.gradient(total_loss, cfg['init_image']), all_loss

emrectn / compute_losses.py

Created April 5, 2020 12:53

	def compute_loss(model, loss_weights, init_image, gram_style_features, content_features):
	"""This function will compute the loss total loss.

	Arguments:
	model: The model that will give us access to the intermediate layers
	loss_weights: The weights of each contribution of each loss function.
	(style weight, content weight, and total variation weight)
	init_image: Our initial base image. This image is what we are updating with
	our optimization process. We apply the gradients wrt the loss we are
	calculating to this image.

emrectn / style_loss.py

Created April 5, 2020 12:52

	def gram_matrix(input_tensor):
	# We make the image channels first
	channels = int(input_tensor.shape[-1])
	a = tf.reshape(input_tensor, [-1, channels])
	n = tf.shape(a)[0]
	gram = tf.matmul(a, a, transpose_a=True)
	return gram / tf.cast(n, tf.float32)

	def get_style_loss(base_style, gram_target):
	"""Expects two images of dimension h, w, c"""

emrectn / get_model.py

Created April 5, 2020 12:52

	def get_model():
	""" Creates our model with access to intermediate layers.

	This function will load the VGG19 model and access the intermediate layers.
	These layers will then be used to create a new model that will take input image
	and return the outputs from these intermediate layers from the VGG model.

	Returns:
	returns a keras model that takes image inputs and outputs the style and
	content intermediate layers.

Emre Çetin emrectn