I am new to deep learning, and am trying to convert this sequential API into a functional API to run on the CIFAR 10 dataset. Below is the sequential API:
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu')
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))
And here is my attempt at converting this into the functional API:
model_input = Input(shape=input_shape)
x = Conv2D(32, (3, 3), activation='relu',padding='valid')(model_input)
x = MaxPooling2D((2,2))(x)
x = Conv2D(32, (3, 3), activation='relu')(x)
x = MaxPooling2D((2,2))(x)
x = Conv2D(32, (3, 3))(x)
x = GlobalAveragePooling2D()(x)
x = Activation(activation='softmax')(x)
model = Model(model_input, x, name='nin_cnn')
x = layers.Flatten()
x = layers.Dense(64, activation='relu')
x = layers.Dense(10)
Here is the compile and train code:
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
history = model.fit(train_images, train_labels, epochs=10,
validation_data=(test_images, test_labels))
The original sequential API gets an accuracy of 0.7175999879837036, while the functional API gets an accuracy of 0.0502999983727932. Not sure where I have gone wrong when re-writing the code, any help would be appreciated. Thanks.
Your two models are not the same. The second and third convolutional layers are having 64 units and 32 units respectively for sequential and functional model in your sample code. And you did not include fully-connected layer in your functional model (you created those layer only after you constructed the model).
If you doubt in the future, you can try to do
model.summary()
and compare to see if the models are the same.
In addition what #adrtam mentioned, I want to add few more as the user is beginner.
There are couple of important difference between Sequential and Functional models. Functional and Sequential are almost similar except,
So Sequential is single-input and single-output, and layers can be added/stacked layer by layer. Functional is more flexibility for customization. So, in a way we can say Sequential is subset of Functional Model.
Coming to your case,
Here is a Sequential model
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import models
input_shape=(32, 32, 3)
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=input_shape))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))
Here is Functional Model.
from tensorflow.keras import Model
from tensorflow.keras import layers
model_input = layers.Input(shape=input_shape)
x = layers.Conv2D(32, (3, 3), activation='relu',padding='valid')(model_input)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)
x = layers.MaxPooling2D((2,2))(x)
x = layers.Conv2D(64, (3, 3), activation='relu')(x)
x = layers.Flatten()(x)
x = layers.Dense(64, activation='relu')(x)
x = layers.Dense(10)(x)
model2 = Model(model_input, x, name='nin_cnn')
Related
My keras model seems to have to hit a saddle point in it's training. Of course this is just an assumption; I'm not really sure. In any case, the loss stops at .0025 and nothing I have tried has worked to reduce the loss any further.
What I have tried so far is:
Using Adam and RMSProp with and without cyclical learning rates. The Results are that the loss starts and stays .0989. The learning rates for cyclical learning where .001 to .1.
After 4 or 5 epochs of not moving I tried SGD instead and the loss steadily declined too .0025. This is where the learning rate stalls out. After about 5 epochs of not changing I tried using SGD with cyclical learning enabled hoping it would decrease but I get the same result.
I have tried increasing network capacity (as well as decreasing) thinking maybe the network hit it's learning limitations. I increased all 4 dense layers to 4096. That didn't change anything.
I've tried different batch sizes.
The most epochs I have trained the network for is 7. However, for 6 of those epochs the loss or validation loss do not change. Do I need to train for more epochs or could it be that .0025 is not a saddle point but is the global minimum for my dataset? I would think there is more room for it to improve. I tested the predictions of the network at .0025 and they aren't that great.
Any advice on how to continue? My code is below.
For starters my keras model is similar in style to VGG-16:
# imports
pip install -q -U tensorflow_addons
import tensorflow_addons as tfa
import tensorflow as tf
from tensorflow import keras
from keras import layers
def get_model(input_shape):
input = keras.input(shape=input_shape)
x = layers.Conv2D(filters=64, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=64, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.MaxPooling2D(pool_size=(2, 2) strides=none, paddings="same")(x)
x = layers.Conv2D(filters=128, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=128, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.MaxPooling2D(pool_size=(2, 2) strides=none, paddings="same")(x)
x = layers.Conv2D(filters=256, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=256, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=256, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=256, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.MaxPooling2D(pool_size=(2, 2) strides=none, paddings="same")(x)
x = layers.Conv2D(filters=512, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=512, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=512, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.Conv2D(filters=512, kernel_size= (3, 3), activation='relu', paddings="same")(input)
x = layers.MaxPooling2D(pool_size=(2, 2) strides=none, paddings="same")(x)
x = layers.Flatten()(x)
x = layers.Dense(4096, activation='relu')(x)
x = layers.Dense(2048, activation='relu')(x)
x = layers.Dense(1024, activation='relu')(x)
x = layers.Dense(512, activation='relu')(x)
output = layers.Dense(9, activation='sigmoid')(x)
return keras.models.Model(inputs=input, outputs=output)
# define learning rate range
lr_range = [.001, .1]
epochs = 100
batch_size = 32
# based on https://www.tensorflow.org/addons/tutorials/optimizers_cyclicallearningrate
steps_per_epoch = len(training_data)/batch_size
clr = tfa.optimizers.CyclicalLearningRate(initial_learning_rate=lr_range[0],
maximal_learning_rate=lr_range[1],
scale_fn=lambda x: 1/(2.**(x-1)),
step_size=2 * steps_per_epoch
)
optimizer = tf.keras.optimizers.Adam(clr)
model = get_model((224, 224, 3))
model.compile(optimzer=optimzer, loss='mean_squared_error')
# used tf.dataset objects for model input
model.fit(train_ds, validation_data=valid_ds, batch_size=batch_size, epochs=epochs)
I am trying to create an image classifier using Keras and TensorFlow 2.0.0 backend.
I'm training this model on my local machine on a custom dataset containing a total of 17~ thousand images. The images vary in size and are located in three different folders (training, validation, and test), each containing two subfolders (one for each class).
I tried an architecture similar to VGG16, which yielded more than decent results on this dataset in the past. Note, there is a minor class imbalance in the data (52:48)
When I call fit_generator(), the model doesn't train well; although the training loss lowers slightly throughout the first epoch, it does not change much afterward. Using this architecture with higher regulation, I achieved 85% accuracy after 55~ epochs in the past.
Imports and hyperparameters
import tensorflow as tf
from tensorflow import keras
from keras import backend as k
from keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Flatten, Input, UpSampling2D
from keras.models import Sequential, Model, load_model
from keras.utils import to_categorical
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ModelCheckpoint
TRAIN_PATH = 'data/train/'
VALID_PATH = 'data/validation/'
TEST_PATH = 'data/test/'
TARGET_SIZE = (256, 256)
RESCALE = 1.0 / 255
COLOR_MODE = 'grayscale'
EPOCHS = 2
BATCH_SIZE = 16
CLASSES = ['Damselflies', 'Dragonflies']
CLASS_MODE = 'categorical'
CHECKPOINT = "checkpoints/weights.hdf5"
Model
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu',
input_shape=(256, 256, 1), padding='same'))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.1))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.1))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.1))
model.add(Flatten())
model.add(Dense(516, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(2, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='Adam', metrics=['accuracy'])
In the past, I created a custom pipeline to reshape, grayscale, flip, and normalize the images; then, I trained the model using my CPU on batches of processed images.
I tried repeating the process using ImageDataGenerator, flow_from_directory, and GPU support.
# randomly flip images, and scale pixel values
trainGenerator = ImageDataGenerator(rescale=RESCALE,
horizontal_flip=True,
vertical_flip=True)
# only scale the pixel values validation images
validatioinGenerator = ImageDataGenerator(rescale=RESCALE)
# only scale the pixel values test images
testGenerator = ImageDataGenerator(rescale=RESCALE)
# instanciate train flow
trainFlow = trainGenerator.flow_from_directory(
TRAIN_PATH,
target_size = TARGET_SIZE,
batch_size = BATCH_SIZE,
classes = CLASSES,
color_mode = COLOR_MODE,
class_mode = CLASS_MODE,
shuffle=True
)
# instanciate validation flow
validationFlow = validatioinGenerator.flow_from_directory(
VALID_PATH,
target_size = TARGET_SIZE,
batch_size = BATCH_SIZE,
classes = CLASSES,
color_mode = COLOR_MODE,
class_mode= CLASS_MODE,
shuffle=True
)
Then, fitting the model using fit_generator.
checkpoints = ModelCheckpoint(CHECKPOINT, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')
with tf.device('/GPU:0'):
model.fit_generator(
trainFlow,
validation_data=validationFlow,
callbacks=[checkpoints],
epochs=EPOCHS
)
I tried training it for 40 epochs.
The classifier achieves 52% after the first epoch and does not improve as time goes by.
Testing the classifier
testFlow = testGenerator.flow_from_directory(
TEST_PATH,
target_size = TARGET_SIZE,
batch_size = BATCH_SIZE,
classes = CLASSES,
color_mode = COLOR_MODE,
class_mode= CLASS_MODE,
)
ans = model.predict_generator(testFlow)
When I look at the predictions, the model predicts all the test images as the majority class with the same confidence [0.48498476, 0.51501524].
Have I made sure the data is correct?
Yes. I tested whether the generators yield processed images and their corresponding labels correctly.
Have I tried changing the loss function, activation function, and optimizer?
Yes. I tried changing the class mode to binary, the loss to binary_crossentropy, and changing the last layer to produce a single output with sigmoid activation. No, I did not change the optimizer. However, I did try to increase the learning rate.
Have I tried changing the model's architecture?
Yes. I tried increasing and decreasing model complexity.
Both more layers with less regularization and fewer layers with more regularization produced similar results.
Are the layers trainable?
Yes.
Is the GPU support implemented correctly?
I hope so.
print("Num GPUs Available: ", len(tf.config.experimental.list_physical_devices('GPU')))
Num GPUs Available: 1
a = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[2, 3], name='a')
b = tf.constant([1.0, 2.0, 3.0, 4.0, 5.0, 6.0], shape=[3, 2], name='b')
c = tf.matmul(a, b)
config = tf.compat.v1.ConfigProto(log_device_placement=True)
config.gpu_options.allow_growth = True
sess = tf.compat.v1.Session(config=config)
print(sess)
Device mapping:
/job:localhost/replica:0/task:0/device:GPU:0 -> device: 0, name: NVIDIA GeForce GTX 1050 with Max-Q Design, pci bus id: 0000:03:00.0, compute capability: 6.1
<tensorflow.python.client.session.Session object at 0x000001F9443E2CC0>
Have I tried transfer learning?
Not yet.
I found a similar unanswered question from 2017 keras-doesnt-train-using-fit-generator.
Thoughts?
The problem is with your model. I copied your code and ran it on a data set I have used before (which gets high accuracy) and got results similar to yours. I then substituted the simple model below
model = tf.keras.Sequential([
Conv2D(16, 3, padding='same', activation='relu', input_shape=(256 , 256,1)),
MaxPooling2D(),
Conv2D(32, 3, padding='same', activation='relu' ),
MaxPooling2D(),
Conv2D(64, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(128, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(256, 3, padding='same', activation='relu'),
MaxPooling2D(),
Flatten(),
Dense(128, activation='relu'),
Dropout(.3),
Dense(64, activation='relu'),
Dropout(.3),
Dense(2, activation='softmax')
])
model.compile(loss='categorical_crossentropy',
optimizer='Adam', metrics=['accuracy'])
The model trained properly. By the way model.fit_generator is depreciated. You can now just use model.fit which can now handle generators. I then took your model and removed all the dropout layers except for the last one and your model trained properly. Code is:
model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3), activation='relu',
input_shape=(256, 256, 1), padding='same'))
model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#model.add(Dropout(0.1))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#model.add(Dropout(0.1))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#model.add(Dropout(0.1))
model.add(Flatten())
model.add(Dense(516, activation='relu'))
#model.add(Dropout(0.1))
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(2, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='Adam', metrics=['accuracy'])
#Gerry P,
By accident, I found what's causing the error.
Removing from Keras import backend as k resolved the model's inability to learn.
That's not all. I also identified that the model you defined, not calling ModelCheckpoint, and not customizing class names affected the fitting process.
model = Sequential([
Conv2D(16, 3, padding='same', activation='relu', input_shape=(256 , 256, 1)),
MaxPooling2D(),
Conv2D(32, 3, padding='same', activation='relu' ),
MaxPooling2D(),
Conv2D(64, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(128, 3, padding='same', activation='relu'),
MaxPooling2D(),
Conv2D(256, 3, padding='same', activation='relu'),
MaxPooling2D(),
Flatten(),
Dense(128, activation='relu'),
Dropout(.3),
Dense(64, activation='relu'),
Dropout(.3),
Dense(2, activation='softmax')
])
I commented that import to try and resolve an error that occurred when I copy-pasted your sequential model. Then, I forgot to uncomment it when I tested it beautiful or average dataset. I achieved over 80% accuracy after the third epoch. Then, I reverted the changes and tried it on my dataset, and it failed again.
As a bonus, not importing Keras's backend decreased the time it takes to train the model!
Lately, I had to re-install Keras and TensorFlow because they couldn't detect my GPU anymore. I probably made a mistake and installed an incompatible version of Keras.
CUDA==10.0
tensorflow-gpu==2.0.0
keras==2.3.1
Note, it's still not a 100% solution, and the problems arise every so often.
EDIT:
Whenever it doesn't work, simplify the model.
Changed batch size and stopped learning? Simplify the model.
Augmented the images further and stopped learning? Simplify the model.
I am trying to configure a network for character recognition of sequential data like license plates.
Now I would like to use the architecture which is noted in Table 3 in Deep Automatic Licence Plate Recognition system (link: http://www.ee.iisc.ac.in/people/faculty/soma.biswas/Papers/jain_icgvip2016_alpr.pdf).
The architecture the authors presented is this one:
The first layers are very common, but where I was stumbling was the top (the part in the red frame) of the architecture. They mention 11 parallel layers and I am really unsure how to get this in Python. I coded this architecture but it does not seem to be right to me.
model = Sequential()
model.add(Conv2D(64, kernel_size=(5, 5), input_shape = (32, 96, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(128, kernel_size=(3, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(256, kernel_size=(3, 3), activation = "relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(1024, activation = "relu"))
model.add(Dense(11*37, activation="Softmax"))
model.add(keras.layers.Reshape((11, 37)))
Could someone help? How do I have to code the top to get an equal architecture like the authors?
The code below can build the architecture described in the image.
import tensorflow as tf
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import Conv2D, Flatten, MaxPooling2D, Dense, Input, Reshape, Concatenate, Dropout
def create_model(input_shape = (32, 96, 1)):
input_img = Input(shape=input_shape)
'''
Add the ST Layer here.
'''
model = Conv2D(64, kernel_size=(5, 5), input_shape = input_shape, activation = "relu")(input_img)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Conv2D(128, kernel_size=(3, 3), input_shape = input_shape, activation = "relu")(model)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Conv2D(256, kernel_size=(3, 3), input_shape = input_shape, activation = "relu")(model)
model = MaxPooling2D(pool_size=(2, 2))(model)
model = Dropout(0.25)(model)
model = Flatten()(model)
backbone = Dense(1024, activation="relu")(model)
branches = []
for i in range(11):
branches.append(backbone)
branches[i] = Dense(37, activation = "softmax", name="branch_"+str(i))(branches[i])
output = Concatenate(axis=1)(branches)
output = Reshape((11, 37))(output)
model = Model(input_img, output)
return model
From my understanding, your implementation is almost correct. The authors train 11 individual classifiers taking as input the output from the Fully Connected Layer. Here, you can think of "parallel" as "independent".
However, you cannot apply the Softmax activation right after the Fully Connected Layer. Since all the classifiers are independent, we want each of them to output a probability for each possible character. Putting things differently, we want the sum of the outputs of each classifier to be 1. Hence, the correct implementation would be:
...
model.add(Dense(1024, activation = "relu"))
# Feeding every neuron with the previous layer's output
model.add(Dense(11*37))
model.add(keras.layers.Reshape((11, 37)))
model.add(keras.activations.softmax(x, axis=1))
I need to train an image classifier using inception V3 model from Keras. The images pass through 5 Conv2D layers and 2 MaxPool2D layers before entering the pre-trained inception V3 model. However my code gives me an error of ValueError: Depth of input (64) is not a multiple of input depth of filter (3) for 'inception_v3_4/conv2d_123/convolution' (op: 'Conv2D') with input shapes: [?,2,2,224], [3,3,3,32]
I reckon my output shape from previous layers is not compatible with the input shape required by Inception. But i am not able to solve it or is it even possible to solve this error. I am a beginner in machine learning and any light in this matter will be greatly appreciated.
My code is as follows:
inception_model = inception_v3.InceptionV3(weights='imagenet', include_top = False)
for layer in inception_model.layers:
layer.trainable = False
input_layer = Input(shape=(224,224,3)) #Image resolution is 224x224 pixels
x = Conv2D(128, (7, 7), padding='same', activation='relu', strides=(2, 2))(input_layer)
x = Conv2D(128, (7, 7), padding='same', activation='relu', strides=(2, 2))(x)
x = Conv2D(64, (7, 7), padding='same', activation='relu', strides=(2, 2))(x)
x = MaxPool2D((3, 3), padding='same',strides=(2, 2))(x)
x = Conv2D(64, (7, 7), padding='same', activation='relu', strides=(2, 2))(x)
x = Conv2D(64, (7, 7), padding='same', activation='relu', strides=(2, 2))(x)
x = MaxPool2D((4, 4), padding='same', strides=(2, 2))(x)
x = inception_model (x) #Error in this line
x = GlobalAveragePooling2D()(x)
predictions = Dense(11, activation='softmax')(x) #I have 11 classes of image to classify
model = Model(inputs = input_layer, outputs=predictions)
model.compile(optimizer=Adam(lr=0.001), loss='categorical_crossentropy', metrics=['acc'])
model.summary()
Like #CAFEBABE said it would be almost useless to do this because the feature map can have almost 3 values but if you still want to try it then you can do this:
x = Conv2D(3, (7, 7), padding='same', activation='relu', strides=(2, 2))(input_layer)
Another thing you will have to remember is that like you used 5 Conv2D and 2 MaxPooling layers above but you can't do that because even in the Inception model there are Conv2D and max-pooling layers which will take the dimensions to negative and give an error. I tried with 2 Conv2D layers and got an error so at max you can use 1.
Also when you are specifying InceptionV3 model specify the input shape.
input_layer = Input(shape=(224,224,3)) #Image resolution is 224x224 pixels
x = Conv2D(128, (7, 7), padding='same', activation='relu', strides=(2, 2))(input_layer)
inception_model = tf.keras.applications.InceptionV3(weights='imagenet', include_top = False, input_shape=x.shape[0])
for layer in inception_model.layers:
layer.trainable = False
x = inception_model (x)
x = GlobalAveragePooling2D()(x)
predictions = Dense(11, activation='softmax')(x) #I have 11 classes of image to classify
model = Model(inputs = input_layer, outputs=predictions)
model.compile(optimizer=Adam(lr=0.001), loss='categorical_crossentropy', metrics=['acc'])
model.summary()
This would work but I doubt it will help the model. Anyways try it who knows what will happen.
I am new to Keras and the Siamese network architecture. I have developed a Siamese network with three inputs and one output as follows.
def get_siamese_model(input_shape):
# Define the tensors for the three input phrases
anchor = Input(input_shape, name='anchor')
positive = Input(input_shape, name='positive')
negative = Input(input_shape, name='negative')
# Convolutional Neural Network
model = Sequential()
model.add(Conv2D(64, kernel_size=(2, 2), activation='relu', input_shape=input_shape, padding='same'))
model.add(Conv2D(32, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(16, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(8, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(4, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(2, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(1, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,1)))
model.add(Flatten())
# Generate the encodings (feature vectors) for the three phrases
anchor_out = model(anchor)
positive_out = model(positive)
negative_out = model(negative)
# Add a customized layer to combine individual output
concat = Lambda(lambda tensors:K.concatenate((tensors[0],tensors[1],tensors[2]),0))
output = concat([anchor_out, positive_out, negative_out])
# Connect the inputs with the outputs
siamese_net = Model(inputs=[anchor,positive,negative],outputs=output)
#plot the model
plot_model(siamese_net, to_file='siamese_net.png',show_shapes=True, show_layer_names=True)
#Error optimization
siamese_net.compile(optimizer=Adam(),
loss=triplet_loss)
# return the model
return siamese_net
while using model.fit() I have written following code:
model = get_siamese_model(input_shape)
X = {
'anchor' : anchor,
'positive' : positive,
'negative' : negative
}
model.fit(np.asarray(X), Y)
I am getting following error message:
ValueError: Error when checking model input:
The list of Numpy arrays that you are passing to your model is not the size the model expected.
Expected to see 3 array(s), but instead got the following list of 1 arrays: [array({'anchor': array([[[[ 4.49218750e-02]...
Any help is appreciated. Thank you in advance.
The following code works for me. Because your names are (anchor, positive, negative), you can use those directly as the keys to your dictionary when passing input. Also, you should make use of the concatenate layer in Keras instead of defining a Lambda. Note that I changed the loss for purposes of this example.
from keras.layers import Input, Conv2D, MaxPooling2D, Flatten, concatenate
from keras.models import Model, Sequential
from keras.optimizers import Adam
from keras.losses import mean_squared_error
import numpy as np
def get_siamese_model(input_shape):
# Define the tensors for the three input phrases
anchor = Input(input_shape, name='anchor')
positive = Input(input_shape, name='positive')
negative = Input(input_shape, name='negative')
# Convolutional Neural Network
model = Sequential()
model.add(Conv2D(64, kernel_size=(2, 2), activation='relu', input_shape=input_shape, padding='same'))
model.add(Conv2D(32, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(16, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(8, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(4, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(2, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(Conv2D(1, kernel_size=(2, 2), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,1)))
model.add(Flatten())
# Generate the encodings (feature vectors) for the three phrases
anchor_out = model(anchor)
positive_out = model(positive)
negative_out = model(negative)
# Add a concatenate layer
output = concatenate([anchor_out, positive_out, negative_out])
# Connect the inputs with the outputs
siamese_net = Model(inputs=[anchor,positive,negative],outputs=output)
# Error optimization
siamese_net.compile(optimizer=Adam(), loss=mean_squared_error)
# Summarize model
siamese_net.summary()
# Return the model
return siamese_net
input_shape = (100, 100, 1)
model = get_siamese_model(input_shape)
X = {'anchor': np.ones((5, 100, 100, 1)), # define input as dictionary
'positive': np.ones((5, 100, 100, 1)),
'negative': np.ones((5, 100, 100, 1))}
Y = np.ones((5, 15000))
model.fit(X, Y) # use a dictionary
model.fit([i for i in X.values()], Y) # use a list