# This Python 3 environment comes with many helpful analytics libraries installed # It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python # For example, here's several helpful packages to load import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) # Input data files are available in the read-only "../input/" directory # For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename)) # You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All" # You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session path='/kaggle/input/competitions/dogs-vs-cats' import zipfile with zipfile.ZipFile(path + "/train.zip", "r") as zip_ref: zip_ref.extractall(".") import os, shutil, pathlib original_dir = pathlib.Path("train") new_base_dir = pathlib.Path("dogs_vs_cats_small") def make_subset(subset_name, start_index, end_index): for category in ("cat", "dog"): dir = new_base_dir / subset_name / category os.makedirs(dir) fnames = [f"{category}.{i}.jpg" for i in range(start_index, end_index)] for fname in fnames: shutil.copyfile(src=original_dir / fname, dst=dir / fname) make_subset("train", start_index=0, end_index=1000) make_subset("validation", start_index=1000, end_index=1500) make_subset("test", start_index=1500, end_index=2500) import keras import os, shutil, pathlib from keras import layers from keras import ops import os import numpy as np import PIL from PIL import Image, ImageChops from keras.datasets import mnist import matplotlib.image as mpimg import matplotlib.pyplot as plt from optree.typing import F import tensorflow as tf from skimage import util, io from skimage.color import rgb2gray from skimage import data import sys from keras.utils import image_dataset_from_directory new_base_dir = pathlib.Path("dogs_vs_cats_small") def cats_and_dogs(): inputs = keras.Input(shape=(180, 180, 3)) x = layers.Rescaling(1.0 / 255)(inputs) x = layers.Conv2D(filters=32, kernel_size=3, activation="relu")(x) x = layers.MaxPooling2D(pool_size=2)(x) x = layers.Conv2D(filters=64, kernel_size=3, activation="relu")(x) x = layers.MaxPooling2D(pool_size=2)(x) x = layers.Conv2D(filters=128, kernel_size=3, activation="relu")(x) x = layers.MaxPooling2D(pool_size=2)(x) x = layers.Conv2D(filters=256, kernel_size=3, activation="relu")(x) x = layers.MaxPooling2D(pool_size=2)(x) x = layers.Conv2D(filters=512, kernel_size=3, activation="relu")(x) x = layers.GlobalAveragePooling2D()(x) x = layers.Dropout(0.25)(x) outputs = layers.Dense(1, activation="sigmoid")(x) model = keras.Model(inputs=inputs, outputs=outputs) return model #------------------------------------------------------------------- #----------- Graficas durante training ----------------------------- class LossHistory(keras.callbacks.Callback): def on_train_begin(self, logs): self.per_batch_losses = [] self.per_batch_val_losses = [] def on_batch_end(self, batch, logs): self.per_batch_losses.append(logs.get("loss")) self.per_batch_val_losses.append(logs.get("val_loss")) import keras_hub conv_base = keras_hub.models.Backbone.from_preset( "xception_41_imagenet", ) conv_base.trainable = True for layer in conv_base.layers[:-4]: layer.trainable = False preprocessor = keras_hub.layers.ImageConverter.from_preset( "xception_41_imagenet", image_size=(180, 180), ) def get_features_and_labels(dataset): all_features = [] all_labels = [] for images, labels in dataset: preprocessed_images = preprocessor(images) features = conv_base.predict(preprocessed_images, verbose=0) all_features.append(features) all_labels.append(labels) return np.concatenate(all_features), np.concatenate(all_labels) #-----------Data augmentation------------------ data_augmentation_layers = [ layers.RandomFlip("horizontal"), layers.RandomRotation(0.1), layers.RandomZoom(0.2), ] def data_augmentation(images, targets): for layer in data_augmentation_layers: images = layer(images) return images, targets #-------------------------------------------------------------------- #-----------Lo datoooo-------------------------------------------- batch_size = 64 image_size = (180, 180) #------------Armado de Train,Test,Validation---------------------------- train_dataset = image_dataset_from_directory( new_base_dir / "train", image_size=image_size, batch_size=batch_size ) validation_dataset = image_dataset_from_directory( new_base_dir / "validation", image_size=image_size, batch_size=batch_size ) test_dataset = image_dataset_from_directory( new_base_dir / "test", image_size=image_size, batch_size=batch_size ) #----------Aumentado de datos--------------------------------------- augmented_train_dataset = train_dataset.map( data_augmentation, num_parallel_calls=8 ) augmented_train_dataset = augmented_train_dataset.prefetch(tf.data.AUTOTUNE) #------------------------------------------------------------------- #train_features, train_labels = get_features_and_labels(train_dataset) #val_features, val_labels = get_features_and_labels(validation_dataset) #test_features, test_labels = get_features_and_labels(test_dataset) inputs = keras.Input(shape=(180, 180, 3)) x = layers.Rescaling(1.0 / 255)(inputs) x = layers.Conv2D(filters=32, kernel_size=5, use_bias=False)(x) for size in [32, 64, 128, 256, 512]: residual = x x = layers.BatchNormalization()(x) x = layers.Activation("relu")(x) x = layers.SeparableConv2D(size, 3, padding="same", use_bias=False)(x) x = layers.BatchNormalization()(x) x = layers.Activation("relu")(x) x = layers.SeparableConv2D(size, 3, padding="same", use_bias=False)(x) x = layers.MaxPooling2D(3, strides=2, padding="same")(x) residual = layers.Conv2D( size, 1, strides=2, padding="same", use_bias=False )(residual) x = layers.add([x, residual]) x = layers.GlobalAveragePooling2D()(x) x = layers.Dropout(0.5)(x) outputs = layers.Dense(1, activation="sigmoid")(x) model = keras.Model(inputs=inputs, outputs=outputs) model.compile( loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"], ) callbacks = [ keras.callbacks.ModelCheckpoint( filepath="fine_tuning.keras", save_best_only=True, monitor="val_loss", ) ] #....................................................................... history = model.fit( augmented_train_dataset, epochs=100, validation_data=validation_dataset, callbacks=callbacks, ) #................................................................... history_dict = history.history loss_values = history_dict["loss"] val_loss_values = history_dict["val_loss"] acc = history_dict["accuracy"] val_acc = history_dict["val_accuracy"] epochs=range(1,len(loss_values)+1) plt.clf() plt.plot(epochs,loss_values,"r--",label="Training loss") plt.plot(epochs,val_loss_values,"b",label="Validation loss") plt.title("Loss evolution during training") plt.xlabel("Epochs") plt.xticks(epochs) plt.ylabel("Loss") plt.legend() plt.savefig("train_val_loss.pdf", format="pdf", bbox_inches="tight") plt.show() #--------------------------------------------------------------------------- #------------------- Validation and Training Accuracy ---------------------- plt.clf() plt.plot(epochs,acc,"r--",label="Training acc") plt.plot(epochs,val_acc,"b",label="Validation acc") plt.title("Accuracy evolution during training") plt.xlabel("Epochs") plt.xticks(epochs) plt.ylabel("Accuracy") plt.legend() plt.savefig("train_val_acc.pdf",format="pdf",bbox_inches="tight") plt.show() plt.clf() floss=open('epochs.dat','a') for i in range(len(epochs)): floss.write(f"{epochs[i]} {loss_values[i]} {val_loss_values[i]} {acc[i]} {val_acc[i]}\n") floss.close