Esempio n. 1
0
"""use python3 Chapter19/visualize_architecture.py"""

from nn.conv.lenet import LeNet
from keras.utils import plot_model

# initialize LeNet and then write the network architecture
# visualization graph to disk
model = LeNet.build(28, 28, 1, 10)
plot_model(model, to_file="Chapter19/lenet.png", show_shapes=True)
Esempio n. 2
0
input_size = n*n*3
sp = SimplePreprocessor(n, n)
iap = ImageToArrayPreprocessor()

sdl = SimpleDatasetLoader(preprocessors=[sp, iap])
(data, labels) = sdl.load(image_paths, verbose=500)
data = data.astype("float") / 255.0

(train_x, test_x, train_y, test_y) = train_test_split(data, labels, test_size=0.25, random_state=42)

train_y = LabelBinarizer().fit_transform(train_y)
test_y = LabelBinarizer().fit_transform(test_y)

print ("[INFO] compiling model...")
opt = SGD(lr=0.005)
model = LeNet.build(width=32, height=32, depth=3, classes=4)
model.compile(loss="categorical_crossentropy", optimizer=opt, metrics=["accuracy"])

print ("[INFO] training network...")
H = model.fit(train_x, train_y, validation_data=(test_x, test_y), batch_size=32, epochs=100, verbose=1)


print("[INFO] evaluating network...")
predictions = model.predict(test_x, batch_size=32)
print(classification_report(test_y.argmax(axis=1), predictions.argmax(axis=1), target_names=["diamonds", "hearts", "spades", "three_sisters"]))


plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, 100), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, 100), H.history["val_loss"], label="val_loss")
Esempio n. 3
0
from keras.utils import plot_model

from nn.conv.lenet import LeNet

model = LeNet.build(width=28, height=28, depth=1, classes=10)
plot_model(model, to_file='lenet.png', show_shapes=True)
Esempio n. 4
0
def main():
    args = option()

    class_name = ['Apple','Avocado','Banana','Coconut','Custard_apple',
                  'Dragon_fruit','Guava','Mango','Orange','Plum',
                  'Start_fruit','Watermelon']

    in_data = 'H5PY/train_normal_128.h5'
    in_label = 'H5PY/labels_train_64_128.h5'

    # import the feature vector and trained labels
    h5f_data  = h5py.File(in_data, 'r')
    h5f_label = h5py.File(in_label, 'r')

    data = h5f_data['dataset']
    labels = h5f_label['dataset']

    data = np.array(data)
    labels = np.array(labels)

    # reshape data matrix
    if K.image_data_format() == "channels_first":
        data = data.reshape(data.shape[0],3,128,128)
    else:
        data = data.reshape(data.shape[0],128,128,3)
    print(data.shape)    
    
    # split training: 80%, testing: 20%
    (trainX, testX, trainY, testY) = train_test_split(data, labels,
                                    test_size=0.20, random_state=42)
    
  
    # convert labels as vector 
    lb = LabelBinarizer()
    trainY = lb.fit_transform(trainY)
    testY = lb.fit_transform(testY)
    
    # initialize the optimizer and model
    print("[INFO] compiling model...")
    opt = SGD(lr=0.05)
    model = LeNet.build(width=128, height=128, depth=3, classes=12)
    model.compile(loss="categorical_crossentropy", optimizer=opt,
                metrics=["accuracy"])
    
    # train the network 
    print("[INFO]training network ...")
    H = model.fit(trainX, trainY, validation_data=(testX,testY),
                batch_size=32, epochs=40, verbose=1)
    
    # save the network to disk 
    print("[INFO] serializing network ...")
    model.save(args["model"])

    # evaluate the network
    print("[INFO] evaluating network...")
    print("[INFO] shape feature: {}".format(data.shape))
    preds = model.predict(testX)
    print(classification_report(testY.argmax(axis=1),
                    preds.argmax(axis=1),
                    target_names=class_name))

    # plot the training loss and accuracy
    plt.style.use("ggplot")
    plt.figure()
    plt.plot(np.arange(0, 40), H.history["loss"], label="train_loss")
    plt.plot(np.arange(0, 40), H.history["val_loss"], label="val_loss")
    plt.plot(np.arange(0, 40), H.history["accuracy"], label="train_acc")
    plt.plot(np.arange(0, 40), H.history["val_accuracy"], label="val_acc")
    plt.title("Training Loss and Accuracy")
    plt.xlabel("Epoch #")
    plt.ylabel("Loss/Accuracy")
    plt.legend()
    plt.savefig(args["output"])