fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images,
test_labels) = fashion_mnist.load_data()
# origin = np.random.randn(3, 28, 28).astype(np.float32)
# input_image = train_images[0, :, :].reshape(1,28,28)
train_images = np.expand_dims(train_images / 255, axis=-1)
test_images = np.expand_dims(test_images / 255, axis=-1)
train_labels = one_hot_f(train_labels, num_classes=10)
test_labels = one_hot_f(test_labels, num_classes=10)
small_train_images = train_images[0:10000]
small_train_labels = train_labels[0:10000]
small_test_images = train_images[0:100]
small_test_labels = train_labels[0:100]
Linear1.compile()
train_iterator = batch_iterator()
acc = test(Linear1, test_images, test_labels)
print('[ acc ]: ', acc)
optimizer = bgd(0.001)
optimizer.fit(Linear1, train_images, train_labels, train_iterator, epoch=10)
acc = test(Linear1, test_images, test_labels)
print('[ acc ]: ', acc)
optimizer.fit(Linear1, train_images, train_labels, train_iterator, epoch=10)
acc = test(Linear1, test_images, test_labels)
print('[ acc ]: ', acc)
optimizer.fit(Linear1, train_images, train_labels, train_iterator, epoch=10)
acc = test(Linear1, test_images, test_labels)
print('[ acc ]: ', acc)
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images,
test_labels) = fashion_mnist.load_data()
# origin = np.random.randn(3, 28, 28).astype(np.float32)
# input_image = train_images[0, :, :].reshape(1,28,28)
train_images = np.expand_dims(train_images / 255, axis=1)
test_images = np.expand_dims(test_images / 255, axis=1)
train_labels = one_hot_f(train_labels, num_classes=10)
test_labels = one_hot_f(test_labels, num_classes=10)
small_train_images = train_images[0:10000]
small_train_labels = train_labels[0:10000]
small_test_images = train_images[0:100]
small_test_labels = train_labels[0:100]
CNN3.compile()
acc = test(CNN3, small_test_images, small_test_labels)
print(acc)
optimizer1 = bgd(0.0001)
optimizer1.fit(CNN3,
small_train_images,
small_train_labels,
epoch=10,
batch_size=16)
CNN3.set_batch_size(1)
acc = test(CNN3, test_images, test_labels)
print(acc)
from models import Linear1
from core.Optimizers import sgd, bgd
from core.Functions import one_hot_f
import numpy as np
from tensorflow import keras
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images,
test_labels) = fashion_mnist.load_data()
# origin = np.random.randn(3, 28, 28).astype(np.float32)
# input_image = train_images[0, :, :].reshape(1,28,28)
train_images = np.expand_dims(train_images / 255, axis=1)
test_images = np.expand_dims(test_images / 255, axis=1)
train_labels = one_hot_f(train_labels, num_classes=10)
test_labels = one_hot_f(test_labels, num_classes=10)
Linear1.compile()
optimizer1 = bgd(0.1)
optimizer1.fit(Linear1, train_images, train_labels, epoch=10, batch_size=16)
optimizer2 = sgd(0.0001)
optimizer2.fit(Linear1, train_images, train_labels, epoch=10, batch_size=1)
if np.argmax(res) == np.argmax(test_label):
cnt_correct += 1
cnt_tot += 1
acc = cnt_correct / cnt_tot
print('[ accuracy ]: ', acc * 100)
return acc
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images,
test_labels) = fashion_mnist.load_data()
train_images = np.expand_dims(train_images / 255, axis=-1)
test_images = np.expand_dims(test_images / 255, axis=-1)
train_labels = one_hot_f(train_labels, num_classes=10)
test_labels = one_hot_f(test_labels, num_classes=10)
CNN5.compile()
try:
CNN5.restore('./CNN5_cuda.param')
except:
pass
train_iterator = batch_iterator(batch_sz=16)
optimizer = bgd(0.1)
for i in range(100):
optimizer.fit(CNN5, train_images, train_labels, train_iterator, epoch=1)
test(CNN5, test_images, test_labels)
CNN5.save('CNN5_cuda')
