95 lines
2.3 KiB
Markdown
95 lines
2.3 KiB
Markdown
# Siamese Neural Network for Keras
|
|
|
|
This project provides a lightweight siamese neural network module for use with the Keras
|
|
framework.
|
|
|
|
The neural network compares two images and returns their similarity in a 0-1 float value.
|
|
The datasets used are the fruit-360 dataset, COCO 2014 and 2017 as well as some ImageNet data.
|
|
|
|
# Installation
|
|
|
|
- tensorflow
|
|
|
|
To install tensorflow:
|
|
```
|
|
$ pip install tensorflow
|
|
```
|
|
|
|
To install tensorflow with gpu support:
|
|
```
|
|
$ pip install tensorflow-gpu
|
|
```
|
|
|
|
- If you use tensorflow-gpu, you'll have to install Cuda and CuDNN.
|
|
|
|
## Usage
|
|
For detailed usage examples please refer to the examples and unit test modules. If the instructions are not sufficient
|
|
feel free to make a request for improvements.
|
|
|
|
- Import the module
|
|
```python
|
|
from siamese import SiameseNetwork
|
|
```
|
|
|
|
- Load or generate some data.
|
|
```python
|
|
x_train = np.random.rand(100, 3)
|
|
y_train = np.random.randint(num_classes, size=100)
|
|
|
|
x_test = np.random.rand(30, 3)
|
|
y_test = np.random.randint(num_classes, size=30)
|
|
```
|
|
|
|
- Design a base model
|
|
```python
|
|
def create_base_model(input_shape):
|
|
model_input = Input(shape=input_shape)
|
|
embedding = Flatten()(model_input)
|
|
embedding = Dense(128)(embedding)
|
|
return Model(model_input, embedding)
|
|
```
|
|
|
|
- Design a head model
|
|
```python
|
|
def create_head_model(embedding_shape):
|
|
embedding_a = Input(shape=embedding_shape)
|
|
embedding_b = Input(shape=embedding_shape)
|
|
|
|
head = Concatenate()([embedding_a, embedding_b])
|
|
head = Dense(4)(head)
|
|
head = BatchNormalization()(head)
|
|
head = Activation(activation='sigmoid')(head)
|
|
|
|
head = Dense(1)(head)
|
|
head = BatchNormalization()(head)
|
|
head = Activation(activation='sigmoid')(head)
|
|
|
|
return Model([embedding_a, embedding_b], head)
|
|
```
|
|
- Create an instance of the SiameseNetwork class
|
|
```python
|
|
base_model = create_base_model(input_shape)
|
|
head_model = create_head_model(base_model.output_shape)
|
|
siamese_network = SiameseNetwork(base_model, head_model)
|
|
```
|
|
|
|
- Compile the model
|
|
```python
|
|
siamese_network.compile(loss='binary_crossentropy', optimizer=keras.optimizers.adam())
|
|
```
|
|
|
|
- Train the model
|
|
```python
|
|
siamese_network.fit(x_train, y_train,
|
|
validation_data=(x_test, y_test),
|
|
batch_size=64,
|
|
epochs=epochs)
|
|
```
|
|
|
|
## requirements
|
|
|
|
keras==2.2.4
|
|
numpy==1.16.4
|
|
pytest==4.6.4
|
|
pep8==1.7.1
|