Python Conv2DClassifier Examples

Example #1

File: conv_2d_clf_mnist_test.py Project: yuyuelovediandian/finch

from conv_2d_clf import Conv2DClassifier
import numpy as np
import tensorflow as tf

if __name__ == '__main__':
    (X_train, y_train), (X_test,
                         y_test) = tf.contrib.keras.datasets.mnist.load_data()
    X_train = (X_train / 255.0)[:, :, :, np.newaxis]
    X_test = (X_test / 255.0)[:, :, :, np.newaxis]

    clf = Conv2DClassifier((28, 28), img_ch=1, n_out=10)
    log = clf.fit(X_train, y_train, val_data=(X_test, y_test))
    pred = clf.predict(X_test)

    final_acc = (pred == y_test).mean()
    print("final testing accuracy: %.4f" % final_acc)

Example #2

File: conv_2d_clf_cifar10_test.py Project: mieitza/finch

from conv_2d_clf import Conv2DClassifier
import numpy as np
import tensorflow as tf


if __name__ == '__main__':
    (X_train, y_train), (X_test, y_test) = tf.keras.datasets.cifar10.load_data()
    X_train = X_train / 255.0
    X_test = X_test / 255.0

    clf = Conv2DClassifier((32, 32), n_out=10)
    log = clf.fit(X_train, y_train, val_data=(X_test, y_test))
    pred = clf.predict(X_test)

    final_acc = (pred == y_test).mean()
    print("final testing accuracy: %.4f" % final_acc)

Example #3

from conv_2d_clf import Conv2DClassifier
import numpy as np
import tensorflow as tf

if __name__ == '__main__':
    mnist = np.load(
        '/media/DB/Student/WHL/finch/tensorflow-models/autoencoder/mnist.npz')
    X_train = mnist['x_train']
    y_train = mnist['y_train']
    X_test = mnist['x_test']
    y_test = mnist['y_test']
    X_train = (X_train / 255.0)[:, :, :, np.newaxis]
    X_test = (X_test / 255.0)[:, :, :, np.newaxis]

    clf = Conv2DClassifier((28, 28), 1, 10)
    log = clf.fit(X_train, y_train, val_data=(X_test, y_test))
    pred = clf.predict(X_test)

    final_acc = (pred == y_test).mean()
    print("final testing accuracy: %.4f" % final_acc)

Example #4

File: conv_2d_clf_cifar10_keras_idg_test.py Project: yang9112/finch-1

from conv_2d_clf import Conv2DClassifier
import tensorflow as tf

BATCH_SIZE = 128
N_EPOCH = 10

if __name__ == '__main__':
    (X_train,
     y_train), (X_test,
                y_test) = tf.contrib.keras.datasets.cifar10.load_data()
    X_train = X_train / 255.0
    X_test = X_test / 255.0

    model = Conv2DClassifier((32, 32), 3, 10)

    datagen = tf.contrib.keras.preprocessing.image.ImageDataGenerator()
    datagen.fit(X_train)

    global_step = 0
    model.sess.run(tf.global_variables_initializer())
    for epoch in range(N_EPOCH):
        for local_step, (X_batch, Y_batch) in enumerate(
                datagen.flow(X_train, y_train, batch_size=BATCH_SIZE)):
            if local_step > len(X_train) // BATCH_SIZE:
                break
            lr = model.decrease_lr(True, global_step, N_EPOCH, len(X_train),
                                   BATCH_SIZE)
            _, loss, acc = model.sess.run(
                [model.train_op, model.loss, model.acc], {
                    model.X: X_batch,
                    model.Y: Y_batch.squeeze(),

Example #5

from conv_2d_clf import Conv2DClassifier
import numpy as np
import tensorflow as tf

if __name__ == '__main__':
    (X_train,
     y_train), (X_test,
                y_test) = tf.contrib.keras.datasets.cifar10.load_data()
    X_train = X_train / 255.0
    X_test = X_test / 255.0

    clf = Conv2DClassifier((32, 32), 3, 10)
    log = clf.fit(X_train, y_train, val_data=(X_test, y_test))
    pred = clf.predict(X_test)

    final_acc = (pred == y_test).mean()
    print("final testing accuracy: %.4f" % final_acc)