data = np.array(data, dtype=float) / 255.0
labels = np.array(labels)
(trainX, testX, trainY, testY) = train_test_split(data,
labels,
test_size=0.25,
random_state=42)
lb = LabelBinarizer().fit(trainY)
trainY = lb.transform(trainY)
testY = lb.transform(testY)
print('[INFO] compiling the model.......')
opt = SGD(lr=0.01)
model = LeNet.build(width=28, height=28, depth=1, classes=9)
model.compile(loss='categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'])
print('[INFO] training the model........')
H = model.fit(trainX,
trainY,
validation_data=(testX, testY),
batch_size=32,
epochs=15,
verbose=1)
print('[INFO] evaluating the network.......')
predictions = model.predict(testX, batch_size=32)
print(
from pyimagesearch.nn.conv.lenet import LeNet from keras.utils import plot_model model = LeNet.build(28, 28, 1, 10) plot_model(model, to_file="lenet.png", show_shapes=True, show_layer_names=True)
import numpy as np
import argparse
import os
# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--include-top", type=int, default=1,
help="whether or not to include top of CNN")
args = vars(ap.parse_args())
# load the VGG16 network, ensuring the head FC layer sets are left
# off
baseModel = VGG16(weights="imagenet", include_top=False,
input_tensor=Input(shape=(224, 224, 3)))
leModel = LeNet.build(64, 64, 3, 10)
# initialize the new head of the network, a set of FC layers
# followed by a softmax classifier
output = Dense(100)(leModel.output)
#headModel = FCHeadNet.build(baseModel, 4, 256)
# place the head FC model on top of the model -- this will
# become the actual model we will train
model = Model(inputs=leModel.input, outputs=output)
# loop over the layers in the network and display them to the
# console
for (i, layer) in enumerate(model.layers):
print("[INFO] {}\t{}".format(i, layer.__class__.__name__))