adriaciurana

#!/bin/bash
DEVICE="HDMI-1"
IS_PRIMARY=`(xrandr --query --verbose | grep "$DEVICE" | cut -d ' ' -f 3)`
if [ "$IS_PRIMARY" == "primary" ]; then
	CURRENT_ORIENTATION=`(xrandr --query --verbose | grep "$DEVICE" | cut -d ' ' -f 6)`
else
	CURRENT_ORIENTATION=`(xrandr --query --verbose | grep "$DEVICE" | cut -d ' ' -f 5)`
fi

ORIENTATION_1="normal"

adriaciurana

import numpy as np

class Optimizer:
	def __init__(self, mu=0.9, lr=0.01):
		self.cache = {}
		self.mu = mu
		self.lr = lr

	def update(self, name_w, old_w, dw):
		if name_w in self.cache:

adriaciurana

Epoch 50/50
...
2000/2000 [==============================] - 158s 79ms/step - loss: 0.1001 - binary_accuracy: 0.9613 - val_loss: 0.6304 - val_binary_accuracy: 0.8426

adriaciurana

raw_results = model.predict(images)
results = {}
labels = {0: 'cat', 1: 'dog'}
text_to_show = {'cat': 'meowww', 'dog': 'bupp'}

def drawText(im, text, color):
	text_size = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 1, 2)[0]
	text_pos_x = (im.shape[1] - text_size[0]) // 2
	text_pos_y = (im.shape[0] + text_size[1]) // 2

adriaciurana

# Cargamos la imagen/imagenes
if os.path.isdir(args.image):
	path_images = []
	for ext in ['jpg', 'jpeg', 'tiff', 'png', 'gif']:
		path_images += glob.glob(os.path.join(args.image, "*." + ext))
else:
	path_images = [args.image]

images = []
for path_im in path_images:

adriaciurana

# Cargamos el modelo
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights("model.h5")

adriaciurana

import argparse, keras, os, cv2
from keras.models import model_from_json
parser = argparse.ArgumentParser()
parser.add_argument("image", help="Image or folder of images to predict",
                    type=str)
args = parser.parse_args()

adriaciurana

import argparse, keras, os
from keras.models import model_from_json
parser = argparse.ArgumentParser()
parser.add_argument("image", help="Image or folder of images to predict",
                    type=str)
args = parser.parse_args()

# Cargamos el modelo
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()

adriaciurana

# Usamos fit generator para aprender.
# Definimos 50 epocas y 2000 iteraciones/epoca
# Indicamos que datos usaremos para validar el correcto aprendizaje y diagnostico
model.fit_generator(
        train_generator,
        steps_per_epoch=2000,
        epochs=50,
        validation_data=val_generator,
        validation_steps=800)

adriaciurana

# Usamos el optimizador Adam
# Usamos la loss function binary_crossentropy. Esta es util cuando la red devuelve una probabilidad, es este caso ser perro o ser gato.
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['binary_accuracy'])
model.summary()