64 lines
2.0 KiB
Python
64 lines
2.0 KiB
Python
from tensorflow.keras.models import load_model
|
|
import os
|
|
import pickle
|
|
import urllib.request as http
|
|
from zipfile import ZipFile
|
|
from tensorflow.keras import utils
|
|
|
|
import tensorflow as tf
|
|
import numpy as np
|
|
from PIL import Image
|
|
|
|
from tensorflow.keras import layers as keras_layers
|
|
from tensorflow.keras import backend as K
|
|
from tensorflow.keras.datasets import cifar10
|
|
from tensorflow.keras.models import save_model, load_model
|
|
|
|
|
|
def load_cifar10(num_classes=3):
|
|
"""
|
|
Downloads CIFAR-10 dataset, which already contains a training and test set,
|
|
and return the first `num_classes` classes.
|
|
Example of usage:
|
|
|
|
>>> (x_train, y_train), (x_test, y_test) = load_cifar10()
|
|
|
|
:param num_classes: int, default is 3 as required by the assignment.
|
|
:return: the filtered data.
|
|
"""
|
|
(x_train_all, y_train_all), (x_test_all, y_test_all) = cifar10.load_data()
|
|
|
|
fil_train = tf.where(y_train_all[:, 0] < num_classes)[:, 0]
|
|
fil_test = tf.where(y_test_all[:, 0] < num_classes)[:, 0]
|
|
|
|
y_train = y_train_all[fil_train]
|
|
y_test = y_test_all[fil_test]
|
|
|
|
x_train = x_train_all[fil_train]
|
|
x_test = x_test_all[fil_test]
|
|
|
|
return (x_train, y_train), (x_test, y_test)
|
|
|
|
if __name__ == '__main__':
|
|
|
|
_, (x_test, y_test) = load_cifar10()
|
|
|
|
x_test_n = x_test / 255
|
|
y_test_n = utils.to_categorical(y_test, 3)
|
|
|
|
lrs = ["01", "0001"]
|
|
nns = [16, 64]
|
|
|
|
for lr in lrs:
|
|
for nn in nns:
|
|
# Load the trained models
|
|
model_task1 = load_model('nn_task1_bonus/t1_bonus_%s_%d.h5' % (lr, nn))
|
|
|
|
# Predict on the given samples
|
|
y_pred_task1 = model_task1.predict(x_test_n)
|
|
|
|
# Evaluate the missclassification error on the test set
|
|
assert y_test_n.shape == y_pred_task1.shape
|
|
test_loss, test_accuracy = model_task1.evaluate(x_test_n, y_test_n) # evaluate accuracy with proper function
|
|
print("Accuracy model task 1 (%d neurons, 0.%s learning rate):" % (nn, lr), test_accuracy)
|