RaphaelMeudec

#!/usr/bin/python3
from datetime import datetime

import psutil


DEFAULT_DRAGO_NICENESS_VALUE = 5
DURATION_BEFORE_RENICING = 30

RaphaelMeudec

"""
Performance comparison between ImageDataGenerator and tf.data.Dataset on a simple task

Dependencies available at https://www.github.com/sicara/tf2-evonorm
"""
import math
from pathlib import Path

import click
import tensorflow as tf

RaphaelMeudec

policy = tf.keras.mixed_precision.experimental.Policy('mixed_float16')
tf.keras.mixed_precision.experimental.set_policy(policy) 

RaphaelMeudec

# Define multi-gpu strategy 
mirrored_strategy = tf.distribute.MirroredStrategy()
# Update batch size value
batch_size *= mirrored_strategy.num_replicas_in_sync
# Create strategy scope to perform training
with mirrored_strategy.scope():
    model = [...]
    model.fit(...)

RaphaelMeudec

from pathlib import Path

import tensorflow as tf

def select_patch(sharp, blur, patch_size_x, patch_size_y):
    """
    Select a patch on both sharp and blur images at the same localization.
    Args:
        sharp (tf.Tensor): Tensor for the sharp image
        blur (tf.Tensor): Tensor for the blur image

RaphaelMeudec

from pathlib import Path

import tensorflow as tf

def select_patch(sharp, blur, patch_size_x, patch_size_y):
    """
    Select a patch on both sharp and blur images at the same localization.

    Args:
        sharp (tf.Tensor): Tensor for the sharp image

RaphaelMeudec

def build_k_way_n_shot_dataset(annotations, n_shot, k_way, classes=None, to_categorical=True, training=True):
    """Build a dataset where each batch contains only N elements of K classes among all classes"""
    # Prepare a dataframe with "image_path", "x1", "x2", "y1", "y2" columns
    annotations = annotations.assign(label=pd.Categorical(annotations.label, categories=classes))

    # Prepare labels as one hot vectors
    targets = annotations.label.cat.codes
    if to_categorical:
        targets = (
            pd.get_dummies(targets)

RaphaelMeudec

with tf.GradientTape() as tape:
    conv_outputs, predictions = grad_model(np.array([img]))
    loss = predictions[:, CAT_CLASS_INDEX]

output = conv_outputs[0]
grads = tape.gradient(loss, conv_outputs)[0]

# Apply guided backpropagation
gate_f = tf.cast(output > 0, 'float32')
gate_r = tf.cast(grads > 0, 'float32')

RaphaelMeudec

import cv2
import numpy as np
import tensorflow as tf

IMAGE_PATH = './cat.jpg'
LAYER_NAME = 'block5_conv3'
CAT_CLASS_INDEX = 281

img = tf.keras.preprocessing.image.load_img(IMAGE_PATH, target_size=(224, 224))
img = tf.keras.preprocessing.image.img_to_array(img)

RaphaelMeudec

import cv2
import numpy as np
import tensorflow as tf

IMAGE_PATH = './cat.jpg'
LAYER_NAME = 'block5_conv3'
CAT_CLASS_INDEX = 281

img = tf.keras.preprocessing.image.load_img(IMAGE_PATH, target_size=(224, 224))
img = tf.keras.preprocessing.image.img_to_array(img)