I have a lot of problem with subclassing models. I want to change this code from functional to subclass model But I received some errors.
class CTCLayer(layers.Layer):
def __init__(self, name=None):
super().__init__(name=name)
self.loss_fn = keras.backend.ctc_batch_cost
def call(self, y_true, y_pred):
# Compute the training-time loss value and add it
# to the layer using `self.add_loss()`.
batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")
input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")
loss = self.loss_fn(y_true, y_pred, input_length, label_length)
self.add_loss(loss)
# At test time, just return the computed predictions
return y_pred
def build_model():
# Inputs to the model
input_img = layers.Input(
shape=(img_width, img_height, 1), name="image", dtype="float32"
)
labels = layers.Input(name="label", shape=(None,), dtype="float32")
# First conv block
x = layers.Conv2D(
32,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv1",
)(input_img)
x = layers.MaxPooling2D((2, 2), name="pool1")(x)
# Second conv block
x = layers.Conv2D(
64,
(3, 3),
activation="relu",
kernel_initializer="he_normal",
padding="same",
name="Conv2",
)(x)
x = layers.MaxPooling2D((2, 2), name="pool2")(x)
# We have used two max pool with pool size and strides 2.
# Hence, downsampled feature maps are 4x smaller. The number of
# filters in the last layer is 64. Reshape accordingly before
# passing the output to the RNN part of the model
new_shape = ((img_width // 4), (img_height // 4) * 64)
x = layers.Reshape(target_shape=new_shape, name="reshape")(x)
x = layers.Dense(64, activation="relu", name="dense1")(x)
x = layers.Dropout(0.2)(x)
# RNNs
x = layers.Bidirectional(layers.LSTM(128, return_sequences=True, dropout=0.25))(x)
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True, dropout=0.25))(x)
# Output layer
x = layers.Dense(
len(char_to_num.get_vocabulary()) + 1, activation="softmax", name="dense2"
)(x)
# Add CTC layer for calculating CTC loss at each step
output = CTCLayer(name="ctc_loss")(labels, x)
# Define the model
model = keras.models.Model(
inputs=[input_img, labels], outputs=output, name="ocr_model_v1"
)
# Optimizer
opt = keras.optimizers.Adam()
# Compile the model and return
model.compile(optimizer=opt)
return model
I want to convert above code to following code:
class CTCLayer(layers.Layer):
def __init__(self, name=None):
super().__init__(name=name)
self.loss_fn = keras.backend.ctc_batch_cost
def call(self, y_true, y_pred):
# Compute the training-time loss value and add it
# to the layer using `self.add_loss()`.
batch_len = tf.cast(tf.shape(y_true)[0], dtype="int64")
input_length = tf.cast(tf.shape(y_pred)[1], dtype="int64")
label_length = tf.cast(tf.shape(y_true)[1], dtype="int64")
input_length = input_length * tf.ones(shape=(batch_len, 1), dtype="int64")
label_length = label_length * tf.ones(shape=(batch_len, 1), dtype="int64")
loss = self.loss_fn(y_true, y_pred, input_length, label_length)
self.add_loss(loss)
# At test time, just return the computed predictions
return y_pred
class ConvBlock(layers.Layer):
def __init__(self, n_filter:int, activation:str, kernel_initializer:str):
super(ConvBlock, self).__init__()
self.conv2d = Conv2D(n_filter, (3, 3), activation=activation,
kernel_initializer=kernel_initializer,
padding="same")
self.maxpool = MaxPooling2D()
def call(self, inputs):
x = self.conv2d(inputs)
x = self.maxpool(x)
return x
class RNNBlock(layers.Layer):
def __init__(self, unit_rnn_1:int, drop_rnn_1:float, unit_rnn_2:int, drop_rnn_2:float):
super(RNNBlock, self).__init__()
self.rnn_1 = Bidirectional(LSTM(unit_rnn_1, return_sequences=True, dropout=drop_rnn_1))
self.rnn_2 = Bidirectional(LSTM(unit_rnn_2, return_sequences=True, dropout=drop_rnn_2))
def call(self, inputs):
x = self.rnn_1(inputs)
x = self.rnn_2(x)
return x
class OCRModel(Model):
def __init__(self, block_1:int=32, act:str='elu', init_kernel:str='he_normal',
block_2:int=64, new_shape:tuple=(50, 768), unit_1:int=64,
drop:float=0.2, unit_rnn_1:int=128, drop_rnn_1:float=0.25,
unit_rnn_2:int=64, drop_rnn_2:float=0.25):
super(OCRModel, self).__init__()
# CNNs
self.b1 = ConvBlock(block_1, act, init_kernel)
self.b2 = ConvBlock(block_2, act, init_kernel)
self.reshape = Reshape(target_shape=new_shape)
self.dense1 = Dense(unit_1, act)
self.drop = Dropout(drop)
#RNNs
self.rnn = RNNBlock(unit_rnn_1, drop_rnn_1, unit_rnn_2, drop_rnn_2)
# Output layer
self.dense2 = Dense(len(char_to_num.get_vocabulary()) + 1, activation="softmax")
# CTC Loss
self.ctc = CTCLayer()
def call(self, inputs):
x = self.b1(inputs[0])
x = self.b2(x)
x = self.reshape(x)
x = self.dense1(x)
x = self.drop(x)
x = self.rnn(x)
x = self.dense2(x)
output = self.ctc(inputs[1], x)
return output
model = OCRModel()
img_input = Input(shape=(img_width, img_height, 1))
label_input = Input(shape=(None, ))
output = model([img_input, label_input])
model = Model(inputs=[img_input, label_input], outputs = output)
model.compile(optimizer='adam')
model.summary()
When I want to start training with following code:
epochs = 100
early_stopping_patience = 10
# Add early stopping
early_stopping = keras.callbacks.EarlyStopping(
monitor="val_loss", patience=early_stopping_patience, restore_best_weights=True
)
# Train the model
history = model.fit(
train_dataset,
validation_data=validation_dataset,
epochs=epochs,
callbacks=[early_stopping],
)
I received this error:
ValueError: Missing data for input "input_7". You passed a data dictionary with keys ['image', 'label']. Expected the following keys: ['input_7', 'input_8']
I don't have any ideas to fix my problem for first what is my problem and at second how can I handle it before it I trained functional model and It worked but when I want to train with my subclass model I received error