def create_model():
base_model = EfficientNetB3(weights='imagenet', include_top=False)
x = base_model.output
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(256, activation='relu')(x)
x = layers.Dropout(0.25)(x)
predictions = layers.Dense(3, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
return model
def efficientnet(b,
weights='imagenet',
include_top=False,
input_shape=(None, None, 3)):
"""Loads the appropriate EfficientNet model with weights
:param b: The size of the EfficientNet model.
:type b: int
:param weights: The pretrained weights to load. Defaults to iamgenet.
:type weights: str
:param include_top: Include the pretrained softmax layer. Defaults to False
:type include_top: bool
:param input_shape: Shape of input images. Defaults to no hight or width, 3 channels.
:type input_shape: Tuple
:return: EfficientNet Model.
:rtype: tf.keras.models.Model
"""
if b == 0:
return EfficientNetB0(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 1:
return EfficientNetB1(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 2:
return EfficientNetB2(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 3:
return EfficientNetB3(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 4:
return EfficientNetB4(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 5:
return EfficientNetB5(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 6:
return EfficientNetB6(weights=weights,
include_top=include_top,
input_shape=input_shape)
elif b == 7:
return EfficientNetB7(weights=weights,
include_top=include_top,
input_shape=input_shape)
else:
raise Exception("Invalid size for EfficientNet")
def load_effnet(shape, efftype = 'B0', weights = 'imagenet', trainable = False):
if efftype == 'B0':
backbone = EfficientNetB0(weights = weights, include_top = False, input_shape = shape)
if efftype == 'B3':
backbone = EfficientNetB3(weights = weights, include_top = False, input_shape = shape)
if efftype == 'B5':
backbone = EfficientNetB5(weights = weights, include_top = False, input_shape = shape)
for layer in backbone.layers:
layer.trainable = trainable
return backbone
brightness_range=(0.9, 1.1))
train_generator = traindatagen.flow_from_dataframe(dataframe=data_train,
x_col='file_path',
y_col='class',
target_size=(300, 300),
batch_size=batch_size)
val_generator = valdatagen.flow_from_dataframe(dataframe=data_test,
x_col='file_path',
y_col='class',
target_size=(300, 300),
batch_size=batch_size)
esiverkko = EfficientNetB3(include_top=False,
weights='imagenet',
input_shape=(300, 300, 3))
verkko = models.Sequential()
verkko.add(esiverkko)
verkko.add(layers.GlobalMaxPooling2D())
verkko.add(layers.Dropout(rate=0.2))
# verkko.add(layers.Dense(1000, activation = 'relu', kernel_initializer = 'he_uniform')) # for InceptionV3
# verkko.add(layers.Dropout(rate = 0.70)) # for InceptionV3
# verkko.add(layers.BatchNormalization()) # for InceptionV3
verkko.add(
layers.Dense(17, activation='softmax',
kernel_initializer='he_uniform'))
verkko.compile(loss='categorical_crossentropy',
optimizer=optimizers.RMSprop(lr=1e-5),
VALID_STEP_PER_EPOCH = tf.math.ceil(valid_images_len / BATCH_SIZE).numpy()
# 기본 Dataset 만들기
# Cutmix 포함 Dataset 만들기
train_ds = make_tf_dataset(train_images, train_labels)
train_ds = train_ds.repeat().batch(BATCH_SIZE).map(cutmix).prefetch(
tf.data.experimental.AUTOTUNE) # tf.data.experimental.AUTOTUNE
valid_ds = make_tf_dataset(valid_images, valid_labels)
valid_ds = valid_ds.repeat().batch(BATCH_SIZE).prefetch(
tf.data.experimental.AUTOTUNE)
base_model = EfficientNetB3(input_shape=(IMG_SIZE, IMG_SIZE, 3),
weights="imagenet",
include_top=False)
avg = tf.keras.layers.GlobalAveragePooling2D()(base_model.output)
output = tf.keras.layers.Dense(train_labels_len, activation="softmax")(avg)
model = tf.keras.Model(inputs=base_model.input, outputs=output)
#model = multi_gpu_model(model, gpus=3)
for layer in base_model.layers:
layer.trainable = True
def build_lrfn(lr_start=0.00001,
lr_max=0.00005,
lr_min=0.00001,
lr_rampup_epochs=5,
lr_sustain_epochs=0,
action="store_true")
args = parser.parse_args()
image_byte = tf.io.read_file(args.image)
img = tf.io.decode_jpeg(image_byte)
model = tf.keras.models.load_model(args.model, compile=False)
img_norm = tf.cast(img, tf.float32)
img_norm = img_norm / 255.
lab_img = tfio.experimental.color.rgb_to_lab(img_norm)
l_img = lab_img[:, :, 0]
if args.pretrained_model:
effnet_model = EfficientNetB3(weights='imagenet', include_top=True)
img_resized = tf.image.resize(img, (300, 300))
img_resized = img_resized / 255.
embeddings = effnet_model.predict(tf.expand_dims(img_resized, axis=0))
ab_pred = model.predict([tf.expand_dims(l_img, axis=0), embeddings])
else:
ab_pred = model.predict(tf.expand_dims(l_img, axis=0))
lab_img_recon = np.zeros((256, 256, 3))
lab_img_recon[:, :, 0] = l_img
lab_img_recon[:, :, 1:] = np.squeeze(ab_pred * 128, axis=0)
utils.visualize(ori_img=img,
L=l_img,
pred_color=tf.cast(
def build_model(base_model, input_shape, metrics, loss, loss_weights,
**kwargs):
if base_model == 'resnet50':
from tensorflow.keras.applications import ResNet50
base_model = ResNet50(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'densenet121':
from tensorflow.keras.applications import DenseNet121
base_model = DenseNet121(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb0':
from efficientnet.tfkeras import EfficientNetB0
base_model = EfficientNetB0(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb1':
from efficientnet.tfkeras import EfficientNetB1
base_model = EfficientNetB1(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb2':
from efficientnet.tfkeras import EfficientNetB2
base_model = EfficientNetB2(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb3':
from efficientnet.tfkeras import EfficientNetB3
base_model = EfficientNetB3(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb4':
from efficientnet.tfkeras import EfficientNetB4
base_model = EfficientNetB4(include_top=False,
weights='imagenet',
input_shape=input_shape)
if base_model == 'efficientnetb5':
from efficientnet.tfkeras import EfficientNetB5
base_model = EfficientNetB5(include_top=False,
weights='imagenet',
input_shape=input_shape)
x_in = Input(shape=input_shape)
x = Conv2D(3, (3, 3), padding='same')(x_in)
x = base_model(x)
x = GlobalAvgPool2D()(x)
x = BatchNormalization()(x)
x = Dropout(0.5)(x)
out_grapheme = Dense(168, activation='softmax', name='root')(x)
out_vowel = Dense(11, activation='softmax', name='vowel')(x)
out_consonant = Dense(7, activation='softmax', name='consonant')(x)
model = Model(inputs=x_in,
outputs=[out_grapheme, out_vowel, out_consonant])
model.compile(Adam(lr=0.0001),
metrics=metrics,
loss=loss,
loss_weights=loss_weights)
return model
headModel = Dense(51, activation='softmax')(headModel)
elif network == "EfficientNetB0":
print(network)
train, test, lb2, labelsTest = preprocessing_EfficcientNet()
baseModel = EfficientNetB0(weights=pretraining,
include_top=False,
input_tensor=Input(shape=(224, 224, 3)),
pooling="avg")
headModel = baseModel.output
headModel = Dropout(0.2)(headModel)
headModel = Dense(51, activation='softmax')(headModel)
else:
print(network)
train, test, lb2, labelsTest = preprocessing_EfficcientNet()
baseModel = EfficientNetB3(weights=pretraining,
include_top=False,
input_tensor=Input(shape=(224, 224, 3)),
pooling="avg")
headModel = baseModel.output
headModel = Dropout(0.2)(headModel)
headModel = Dense(51, activation='softmax')(headModel)
corrida = str(corrida)
print("corrida %s" % (corrida))
model = Model(inputs=baseModel.input, outputs=headModel)
for layer in model.layers:
layer.trainable = True
print("[INFO] compiling model...")
opt = SGD()
model.compile(