I want to add attention layer before transfer learning, something like below, however, in the function create_model_tl I do not suppose to pass x yet, how to write a function to create a model so later on I can call the function to create model myModel = create_model_tl(input_shape, mdl_type, weights) and pass for compile and fit?
def attention(v, k, q, d_model, num_heads, mask):
......
return output
def create_model_tl(input_shape, mdl_type, weights):
print("start creating model - transfer learning ...")
conv_layer = Conv2D(16, kernel_size=(1, 1), activation='relu', input_shape=input_shape)
x = conv_layer(x)
x = attention(x, x, x, 16, 4, None) # k, q, v, d_model, num_heads, mask
base_model = vgg16.VGG16(include_top=False, input_shape=(x.shape[1], x.shape[2], x.shape[3], weights=weights)
flat1 = Flatten()(base_model.layers[-1].output)
class1 = Dense(1024, activation='relu')(flat1)
dropout1 = Dropout(0.2)(class1)
class2 = Dense(512, activation='relu')(dropout1)
dropout2 = Dropout(0.2)(class2)
output = Dense(2, activation='softmax')(dropout2)
#output = Dense(1, activation='sigmoid')(dropout2)
model = Model(inputs=base_model.inputs, outputs=output)
return model
Related
Is there a possibility to create my own block using keras
Maybe something like this:
import tensorflow as tf
class NewLayer(tf.keras.layers.Layer):
def __init__(self):
super(NewLayer, self).__init__()
self.dense1 = tf.keras.layers.Dense(64, activation='relu')
self.dense2 = tf.keras.layers.Dense(16, activation='relu')
self.dense3 = tf.keras.layers.Dense(3)
self._name = 'My_model'
def call(self, inputs):
x = tf.keras.layers.Flatten()(inputs)
x = self.dense1(x)
x = self.dense2(x)
output = self.dense3(x)
return output
inputs = tf.keras.layers.Input((128, 128, 3))
x = tf.keras.layers.Conv2D(256, 67)(inputs)
new_layer = NewLayer()
outputs = new_layer(x)
model = tf.keras.Model(inputs, outputs)
dot_img_file = 'model.png'
tf.keras.utils.plot_model(model, to_file=dot_img_file, show_shapes=True)
I am trying to make a model that has lambda layer that executes a custom function the output shape of it is to be of shape `(batch_size, 10, 5)
def yolo_head(x):
boxes_ = x[:,:,:,:,1:5]
confidence_ = x[:,:,:,:,:1]
classes_ = x[:,:,:,:,5:]
scores, boxes, classes = yolo_filter_boxes(boxes_, confidence_, classes_, threshold)
scores, boxes, classes = yolo_non_max_suppression(scores, boxes, classes, max_box, threshold_iou)
classes = tf.cast(classes, tf.float32, name=None)
preds = scores*classes
second_use = 0
use = len(preds.get_shape().as_list())
if use>1:
second_use=preds.get_shape().as_list()[1]
if use==1:
preds = tf.zeros((preds.get_shape().as_list()[0],10,5), dtype=tf.dtypes.float32, name=None)
elif second_use<10:
current = tf.zeros((preds.get_shape().as_list()[0],10-second_use,5), dtype=tf.dtypes.float32, name=None)
preds = tf.reshape(preds, (-1,1), name=None)
preds = tf.concat(axis=1, values=[preds, boxes])
preds = tf.concat(axis=0, values=[preds,current])
else:
preds = tf.reshape(preds, (-1,1), name=None)
preds = tf.concat(axis=1,values=[preds, boxes])
return preds
def create_model():
total_ = 19*19*no_of_anchors*6
pretrained_model = tf.keras.applications.MobileNetV2(
input_shape=(512, 512, 3),
include_top=False,
weights='imagenet',
pooling='max'
)
pretrained_model.trainable = False
inputs = pretrained_model.input
x=tf.keras.layers.Flatten()(pretrained_model.output)
x = tf.keras.layers.Dense(total_, activation='relu',bias_initializer=tf.zeros_initializer(),kernel_initializer=tf.keras.initializers.Ones())(x)
x = tf.keras.layers.Reshape((19, 19, no_of_anchors, 6))(x)
outputs = tf.keras.layers.Lambda(yolo_head)(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
model.compile(
optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy']
)
return model
[1]: https://i.stack.imgur.com/rJXNp.png [This is the output which shows error][1]
This Model is a variety of CNN and uses Causal Dilational Convolution Layer.
I can train and predict with 0 error, but when I use model.save() to save model, it throws Exception.
So I use save_weights and load_weights to save and load model.
I wonder why this error appears：
model.save("path")
out:
ValueError: Dimension size must be evenly divisible by 2 but is 745 for '{{node conv1d_5/SpaceToBatchND}} = SpaceToBatchND[T=DT_FLOAT, Tblock_shape=DT_INT32, Tpaddings=DT_INT32](conv1d_5/Pad, conv1d_5/SpaceToBatchND/block_shape, conv1d_5/SpaceToBatchND/paddings)' with input shapes: [?,745,32], [1], [1,2] and with computed input tensors: input[1] = <2>, input[2] = <[0 0]>.
Input shape is (None,743,27)
Output shape is (None,24,1)
def slice(x, seq_length):
return x[:, -seq_length:, :]
class ResidualBlock(tf.keras.layers.Layer):
def __init__(self, n_filters, filter_width, dilation_rate):
super(ResidualBlock, self).__init__()
self.n_filters = n_filters
self.filter_width = filter_width
self.dilation_rate = dilation_rate
# preprocessing - equivalent to time-distributed dense
self.x = Conv1D(32, 1, padding='same', activation='relu')
# filter convolution
self.x_f = Conv1D(filters=n_filters,
kernel_size=filter_width,
padding='causal',
dilation_rate=dilation_rate,
activation='tanh')
# gating convolution
self.x_g = Conv1D(filters=n_filters,
kernel_size=filter_width,
padding='causal',
dilation_rate=dilation_rate,
activation='sigmoid')
# postprocessing - equivalent to time-distributed dense
self.z_p = Conv1D(32, 1, padding='same', activation='relu')
def call(self, inputs):
x = self.x(inputs)
f = self.x_f(x)
g = self.x_g(x)
z = tf.multiply(f, g)
z = self.z_p(z)
return tf.add(x, z), z
def get_config(self):
config = super(ResidualBlock, self).get_config()
config.update({"n_filters": self.n_filters,
"filter_width": self.filter_width,
"dilation_rate": self.dilation_rate})
return config
class WaveNet(tf.keras.Model):
def __init__(self, n_filters=32, filter_width=2, dilation_rates=None, drop_out=0.2, pred_length=24):
super().__init__(name='WaveNet')
# Layer Parameter
self.n_filters = n_filters
self.filter_width = filter_width
self.drop_out = drop_out
self.pred_length = pred_length
if dilation_rates is None:
self.dilation_rates = [2 ** i for i in range(8)]
else:
self.dilation_rates = dilation_rates
# Layer
self.residual_stacks = []
for dilation_rate in self.dilation_rates:
self.residual_stacks.append(ResidualBlock(self.n_filters, self.filter_width, dilation_rate))
# self.add = Add()
self.cut = Lambda(slice, arguments={'seq_length': pred_length})
self.conv_1 = Conv1D(128, 1, padding='same')
self.relu = Activation('relu')
self.drop = Dropout(drop_out)
self.skip = Lambda(lambda x: x[:, -2 * pred_length + 1:-pred_length + 1, :1])
self.conv_2 = Conv1D(1, 1, padding='same')
def _unroll(self, inputs, **kwargs):
outputs = inputs
skips = []
for residual_block in self.residual_stacks:
outputs, z = residual_block(outputs)
skips.append(z)
outputs = self.relu(Add()(skips))
outputs = self.cut(outputs)
outputs = self.conv_1(outputs)
outputs = self.relu(outputs)
outputs = self.drop(outputs)
outputs = Concatenate()([outputs, self.skip(inputs)])
outputs = self.conv_2(outputs)
outputs = self.cut(outputs)
return outputs
def _get_output(self, input_tensor):
pass
def call(self, inputs, training=False, **kwargs):
if training:
return self._unroll(inputs)
else:
return self._get_output(inputs)
Train step
model = WaveNet()
model.compile(Adam(), loss=loss)
# ok
history = model.fit(train_x, train_y,
batch_size=batch_size,
epochs=epochs,
callbacks=[cp_callback] if save else None)
# ok
result = model.predict(test_x)
# error
model.save("path")
I made this function that incorporates a resnet into a model. It works well, and I can save it.
My problem is that I can't load it because it needs a call function. I am not exactly sure of how to turn this into a class. The attempt is at the bottom. some pointers would be helpful.
def build_network():
inp = Input(shape=(256,256,3))
resnet = tf.keras.applications.ResNet152V2(
include_top=False, weights='imagenet', input_tensor=None,
input_shape=(256,256,3), pooling=None, classes=1000
)
# classifier_activation='softmax'
x = resnet(inp)
x = GlobalAveragePooling2D()(x)
x = Dropout(0.3)(x)
x = Dense(9, activation='softmax')(x)
model = tf.keras.Model(inputs=inp,outputs = x)
opt = tf.keras.optimizers.SGD(momentum=0.9)
# optimizer = 'adam',
model.compile(loss='categorical_crossentropy',
optimizer = opt,
metrics=['accuracy'])
model.summary()
return model
class Resnet(tf.keras.Model):
def __init__(self, num_classes=9):
super(Resnet, self).__init__()
self.block_1 = tf.keras.applications.ResNet152V2(
include_top=False, weights='imagenet', input_tensor=None,
input_shape=(256,256,3), pooling=None, classes=1000)
self.global_pool = layers.GlobalAveragePooling2D()
self.dropout = Dropout(0.3)
self.classifier = Dense(num_classes, activation = 'softmax')
def call(self, inputs):
x = self.block_1(inputs)
x = self.global_pool(x)
x = self.dropout(x)
x = self.classifier(x)
return tf.keras.Model(inputs = inputs, outputs = x)
Using the subclassing API will actually make your model unserializable (see the "Limitations section in the "What are Symbolic and Imperative APIs in TensorFlow 2.0? " blogpost):
Imperative models are also more difficult to inspect, copy, or clone.
For example, model.save(), model.get_config(), and clone_model do not work for subclassed models. Likewise, model.summary() only gives you a list of layers (and doesn’t provide information on how they’re connected, since that’s not accessible).
Edit: From Tensorflow 2.4, it is possible to pass a save_traces argument to model.save to serialize models built using the subclassing API. See https://www.tensorflow.org/guide/keras/save_and_serialize#how_savedmodel_handles_custom_objects.
Here's a simple example of how you can do this:
import tensorflow as tf
from tensorflow.keras.layers import (Dense, Dropout, GlobalAveragePooling2D,
Input)
def build_network():
inp = Input(shape=(256, 256, 3))
resnet = tf.keras.applications.ResNet152V2(include_top=False,
weights="imagenet",
input_tensor=None,
input_shape=(256, 256, 3),
pooling=None,
classes=1000)
# classifier_activation="softmax"
x = resnet(inp)
x = GlobalAveragePooling2D()(x)
x = Dropout(0.3)(x)
x = Dense(9, activation="softmax")(x)
model = tf.keras.Model(inputs=inp, outputs=x)
# optimizer = "adam",
opt = tf.keras.optimizers.SGD(momentum=0.9)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=["accuracy"])
model.summary()
return model
if __name__ == "__main__":
model = build_network()
model.summary()
# Save
model.save("my_model.h5")
# Load
loaded_model = tf.keras.models.load_model("my_model.h5")
loaded_model.summary()
To load your saved model from your build_network function use tf.keras.models.load_model.
I have been working on speech emotion recognition deep neural network. I have used keras Bidirectional LSTM with CTC loss. i trained the model and saved it
model_json = model.to_json()
with open("ctc_model.json", "w") as json_file:
json_file.write(model_json)
model.save_weights("ctc_weights.h5")
The problem is i can not use this model to test on on unseen data because the model accepts 4 argument as input and calculates the ctc loss..just build the model and train. so how can i save a model in such away that in require only one input. not the labels, and length. Basically how can i save a model as this function test_func = K.function([net_input], [output])
def ctc_lambda_func(args):
y_pred, labels, input_length, label_length = args
shift = 2
y_pred = y_pred[:, shift:, :]
input_length -= shift
return K.ctc_batch_cost(labels, y_pred, input_length, label_length)
def build_model(nb_feat, nb_class, optimizer='Adadelta'):
net_input = Input(name="the_input", shape=(200, nb_feat))
forward_lstm1 = LSTM(output_dim=64,
return_sequences=True,
activation="tanh"
)(net_input)
backward_lstm1 = LSTM(output_dim=64,
return_sequences=True,
activation="tanh",
go_backwards=True
)(net_input)
blstm_output1 = Merge(mode='concat')([forward_lstm1, backward_lstm1])
forward_lstm2 = LSTM(output_dim=64,
return_sequences=True,
activation="tanh"
)(blstm_output1)
backward_lstm2 = LSTM(output_dim=64,
return_sequences=True,
activation="tanh",
go_backwards=True
)(blstm_output1)
blstm_output2 = Merge(mode='concat')([forward_lstm2, backward_lstm2])
hidden = TimeDistributed(Dense(512, activation='tanh'))(blstm_output2)
output = TimeDistributed(Dense(nb_class + 1, activation='softmax')) (hidden)
labels = Input(name='the_labels', shape=[1], dtype='float32')
input_length = Input(name='input_length', shape=[1], dtype='int64')
label_length = Input(name='label_length', shape=[1], dtype='int64')
loss_out = Lambda(ctc_lambda_func, output_shape=(1,), name="ctc")([output, labels, input_length, label_length])
model = Model(input=[net_input, labels, input_length, label_length], output=[loss_out])
model.compile(loss={'ctc': lambda y_true, y_pred: y_pred}, optimizer=optimizer, metrics=[])
test_func = K.function([net_input], [output])
return model, test_func
model, test_func = build_model(nb_feat=nb_feat, nb_class=nb_class, optimizer=optimizer)
for epoch in range(number_epoches):
inputs_train = {'the_input': X_train[i:i+batch_size],
'the_labels': y_train[i:i+batch_size],
'input_length': np.sum(X_train_mask[i:i+batch_size], axis=1, dtype=np.int32),
'label_length': np.squeeze(y_train_mask[i:i+batch_size]),
}
outputs_train = {'ctc': np.zeros([inputs_train["the_labels"].shape[0]])}
ctcloss = model.train_on_batch(x=inputs_train, y=outputs_train)
total_ctcloss += ctcloss * inputs_train["the_input"].shape[0] * 1.
loss_train[epoch] = total_ctcloss / X_train.shape[0]
Here is the my model summary
Try the following solution:
import keras.backend as K
def get_prediction_function(model):
input_tensor = model.layers[0].input
output_tensor = model.layers[-5].output
net_function = K.function([input_tensor, K.learning_phase()], [output_tensor])
def _result_function(x):
return net_function([x, 0])[0]
return _result_function
Now your network function might be obtained by:
test_function = get_prediction_function(model)