Herramientas de usuario

Herramientas del sitio


clase:iabd:pia:documentacion

Documentación

Overfitting, validación , reducción de la dimensionalidad, datos entrada

Métricas

Funciones de coste

Redes neuronales

Utilidades

Redes Neuronales Recurrentes, transformers, series de tiempo

Lenguaje Natural

Kaggle

Autoencoders

Redes Convolutionales

AutoML

Estadística Bayesana

Pipelines , MLOps

Gráficos

Correlación

Estadística

Matemáticas

TensorFlow Avanzado

import tensorflow as tf
tf.config.list_physical_devices()

from tensorflow.python.client import device_lib
device_lib.list_local_devices()

device=device_lib.list_local_devices()[0]
with tf.device(device.name):
    history=model.fit(x, y,epochs=epochs,verbose=False)

Natural Language Processing

EDA

Guías

Libros online

Compendios

Humor

Python

Crear un colormap personalizado

from matplotlib.colors import LinearSegmentedColormap, to_rgb

def crear_colomap_continuo(hex_colors):
    all_red = []
    all_green = []
    all_blue = []
    
    for hex_color in hex_colors:
        all_red.append(to_rgb(hex_color)[0])
        all_green.append(to_rgb(hex_color)[1])
        all_blue.append(to_rgb(hex_color)[2])

        
    num_colors = len(hex_colors) - 1
    red = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_red)])
    green = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_green)])
    blue = tuple([(1/num_colors*i,v,v) for i,v in enumerate(all_blue)])
    
    color_dictionary = {'red':red,'green':green,'blue':blue}
    new_cmap = LinearSegmentedColormap('new_cmap',segmentdata=color_dictionary)
    return new_cmap



new_cmap = build_custom_continuous_cmap(["#FFFFFF","#DBE6FA","#C3D6F4","#ACC8EF","#96BBE9","#81AFE4","#6DA4DE","#599BD9","#4793D3","#358CCE","#2486C8","#1481C3","#057DBD"])

Hardware

clase/iabd/pia/documentacion.txt · Última modificación: 2023/09/22 16:01 por admin