def visualize_network(
network,
scale_xy: int = 2,
spacing: int = 10,
scale_z=0.1,
save_image_path: str = None,
):
try:
font = ImageFont.truetype(ImageFontPath.SKIA, 16)
color_map = defaultdict(dict)
color_map[Conv2D]['fill'] = '#CA6F1E'
color_map[Activation]['fill'] = "#662851"
color_map[Dropout]['fill'] = '#212F3D'
color_map[MaxPooling2D]['fill'] = '#006fC1'
color_map[Dense]['fill'] = '#145A32'
color_map[Flatten]['fill'] = '#229954'
color_map[BatchNormalization]['fill'] = '#BDC3C7'
color_map[AveragePooling2D]['fill'] = '#4EACF2'
color_map[Concatenate]['fill'] = "#4A235A"
return visualkeras.layered_view(
network,
color_map=color_map,
font=font,
legend=True,
scale_xy=scale_xy,
spacing=spacing,
to_file=save_image_path,
scale_z=scale_z,
)
except Exception as e:
raise e
def save_report_keras(model, datasets, classes, history, name, save_path):
report_dist_path = "../reports/" + save_path
title_page = get_title_page(name)
model_summary = get_model_summary(model)
loss = plot_graph(
[[history['loss'], 'Training data']
], # [history['val_loss'], 'Validation data']
name="Training losses",
legend=['Loss', 'No. epoch'])
accuracy = plot_graph(
[[history['accuracy'], 'Training data']
], # [history['val_accuracy'], 'Validation data']
name="Model accuracy",
legend=['Accuracy', 'No. epoch'])
if not os.path.exists(report_dist_path):
os.mkdir(report_dist_path)
pp = PdfPages(report_dist_path + "/" + name + '.pdf')
pp.savefig(title_page)
pp.savefig(model_summary)
model_image = set_image(
visualkeras.layered_view(model,
legend=True,
scale_xy=2,
scale_z=1,
draw_funnel=False,
min_z=10,
min_xy=10,
max_z=200,
max_xy=1000))
pp.savefig(model_image)
pp.savefig(loss)
pp.savefig(accuracy)
for ds, title in datasets:
y_true, y_pred = generate_y_with_dense(model, ds)
confusion_matrix = plot_confusion_matrix(y_true,
y_pred,
title=title,
classes=classes)
pp.savefig(confusion_matrix)
pp.close()
def visualize_model(self):
color_map = defaultdict(dict)
color_map[Convolution2D]['fill'] = 'orange'
color_map[Lambda]['fill'] = 'gray'
color_map[Dropout]['fill'] = 'pink'
color_map[Cropping2D]['fill'] = 'red'
color_map[Dense]['fill'] = 'green'
color_map[Flatten]['fill'] = 'blue'
color_map[Activation]['fill'] = 'yellow'
file_name = os.path.join(self.output_dir, "color_output.png")
check_dir(file_name)
visualkeras.layered_view(self.model, color_map=color_map, spacing=50, to_file=file_name)
file_name = os.path.join(self.output_dir, "output.png")
check_dir(file_name)
visualkeras.layered_view(self.model, spacing=50, to_file=file_name) # write to disk
file_name = os.path.join(self.output_dir, "flat_output.png")
check_dir(file_name)
visualkeras.layered_view(self.model, draw_volume=False, spacing=50, to_file=file_name)
file_name = os.path.join(self.output_dir, "model_plot.png")
check_dir(file_name)
plot_model(self.model, to_file=file_name, show_shapes=True, show_layer_names=True)
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax'))
# Now visualize the model!
color_map = defaultdict(dict)
color_map[Conv2D]['fill'] = 'orange'
color_map[ZeroPadding2D]['fill'] = 'gray'
color_map[Dropout]['fill'] = 'pink'
color_map[MaxPooling2D]['fill'] = 'red'
color_map[Dense]['fill'] = 'green'
color_map[Flatten]['fill'] = 'teal'
font = ImageFont.truetype("arial.ttf", 32)
visualkeras.layered_view(model, to_file='../figures/vgg16.png', type_ignore=[visualkeras.SpacingDummyLayer])
visualkeras.layered_view(model, to_file='../figures/vgg16_legend.png', type_ignore=[visualkeras.SpacingDummyLayer],
legend=True, font=font)
visualkeras.layered_view(model, to_file='../figures/vgg16_spacing_layers.png', spacing=0)
visualkeras.layered_view(model, to_file='../figures/vgg16_type_ignore.png',
type_ignore=[ZeroPadding2D, Dropout, Flatten, visualkeras.SpacingDummyLayer])
visualkeras.layered_view(model, to_file='../figures/vgg16_color_map.png',
color_map=color_map, type_ignore=[visualkeras.SpacingDummyLayer])
visualkeras.layered_view(model, to_file='../figures/vgg16_flat.png',
draw_volume=False, type_ignore=[visualkeras.SpacingDummyLayer])
visualkeras.layered_view(model, to_file='../figures/vgg16_scaling.png',
scale_xy=1, scale_z=1, max_z=1000, type_ignore=[visualkeras.SpacingDummyLayer])
baseModel = VGG16(weights="imagenet", include_top=False,
input_tensor=Input(shape=(224, 224, 3)))
headModel = baseModel.output
headModel = AveragePooling2D(pool_size=(7, 7))(headModel)
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(512, activation="relu")(headModel)
headModel = Dense(len(lb.classes_), activation="softmax")(headModel)
model = Model(inputs=baseModel.input, outputs=headModel)
for layer in baseModel.layers:
layer.trainable = False
model.summary()
visualkeras.layered_view(model, to_file='vgg16_arc.png', legend=True)
# compile model
print("[INFO] compiling model...")
opt = SGD(lr=1e-4, momentum=0.9, decay=1e-4 / args["epochs"])
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
# train model
print("[INFO] training head...")
H = model.fit(
x=trainAug.flow(trainX, trainY, batch_size=32),
steps_per_epoch=len(trainX) // 32,
validation_data=valAug.flow(testX, testY),
validation_steps=len(testX) // 32,
epochs=args["epochs"])
# validation_steps = TRAIN_VAL.shape[0] // 64,
verbose=1,
callbacks = [early_stopping_callback, ckpt])
scores = model.evaluate(inputs[test], targets[test], verbose=0)
print(f'Score for fold {fold_no}: {model.metrics_names[0]} of {scores[0]}; {model.metrics_names[1]} of {scores[1]*100}%')
acc_per_fold.append(scores[1] * 100)
loss_per_fold.append(scores[0])
# Increase fold number
fold_no = fold_no + 1
!pip install visualkeras
import visualkeras
visualkeras.layered_view(model)
"""## Evaluation"""
print(TRAIN_VAL.shape)
plt.title('Model Accuracy')
plt.plot(range(1,11),history.history['accuracy'])
plt.plot(range(1,11),history.history['val_accuracy'])
plt.xlabel('Epoch')
plt.ylabel('accuracy')
plt.legend(labels=['train','validation'])
plt.show()
plt.title('Model Loss')
plt.plot(range(1,11),history.history['loss'])
plt.plot(range(1,11),history.history['val_loss'])
from tensorflow.python.keras.models import Sequential
from tensorflow.keras import layers
import visualkeras
model = Sequential()
model.add(layers.Dense(8, activation='relu', input_shape=(4000, )))
model.add(layers.Dense(8, activation='relu'))
model.add(layers.Dense(1, activation='sigmoid'))
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
visualkeras.layered_view(model,
to_file='../figures/spam.png',
min_xy=10,
min_z=10,
scale_xy=100,
scale_z=100,
one_dim_orientation='x')
from tensorflow import keras from tensorflow.keras import layers import visualkeras encoder_input = keras.Input(shape=(28, 28, 1), name='img') x = layers.Conv2D(16, 3, activation='relu')(encoder_input) x = layers.Conv2D(32, 3, activation='relu')(x) x = layers.MaxPooling2D(3)(x) x = layers.Conv2D(32, 3, activation='relu')(x) x = layers.Conv2D(16, 3, activation='relu')(x) encoder_output = layers.GlobalMaxPooling2D()(x) encoder = keras.Model(encoder_input, encoder_output, name='encoder') visualkeras.layered_view(encoder, to_file='../figures/encoder.png') x = layers.Reshape((4, 4, 1))(encoder_output) x = layers.Conv2DTranspose(16, 3, activation='relu')(x) x = layers.Conv2DTranspose(32, 3, activation='relu')(x) x = layers.UpSampling2D(3)(x) x = layers.Conv2DTranspose(16, 3, activation='relu')(x) decoder_output = layers.Conv2DTranspose(1, 3, activation='relu')(x) autoencoder = keras.Model(encoder_input, decoder_output, name='autoencoder') visualkeras.layered_view(autoencoder, to_file='../figures/autoencoder.png')
conv9 = tf.keras.layers.Conv2DTranspose(64,
kshape,
activation='relu',
padding='same',
trainable=base_trainable)(up9)
conv9 = tf.keras.layers.BatchNormalization()(conv9)
conv9 = tf.keras.layers.Conv2DTranspose(64,
kshape,
activation='relu',
padding='same',
trainable=base_trainable)(conv9)
conv9 = tf.keras.layers.BatchNormalization()(conv9)
out = tf.keras.layers.Conv2D(num_classes, (1, 1),
activation='softmax')(conv9)
model = tf.keras.Model(input_img, out)
opt = tf.keras.optimizers.Adam(lr=learning_rate, decay=learning_decay)
model.compile(optimizer=opt, loss='categorical_crossentropy')
return model
model = get_model()
visualkeras.layered_view(model,
to_file='model.png',
type_ignore=[
tf.keras.layers.BatchNormalization,
tf.keras.layers.AlphaDropout
])