Python layers.InputLayer方法代码示例

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def build_model():
    model = Sequential()
    model.add(InputLayer(input_shape=(None, None, 1)))
    model.add(Conv2D(8, (3, 3), activation='relu', padding='same', strides=2))
    model.add(Conv2D(8, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same', strides=2))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same', strides=2))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(32, (3, 3), activation='relu', padding='same'))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(16, (3, 3), activation='relu', padding='same'))
    model.add(UpSampling2D((2, 2)))
    model.add(Conv2D(2, (3, 3), activation='tanh', padding='same'))
    # model.compile(optimizer='rmsprop', loss='mse')
    model.compile(optimizer='adam', loss='mse')
    return model


#训练数据 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def fsrcnn(x, d=56, s=12, m=4, scale=3):
    """Build an FSRCNN model.

    See https://arxiv.org/abs/1608.00367
    """
    model = Sequential()
    model.add(InputLayer(input_shape=x.shape[-3:]))
    c = x.shape[-1]
    f = [5, 1] + [3] * m + [1]
    n = [d, s] + [s] * m + [d]
    for ni, fi in zip(n, f):
        model.add(Conv2D(ni, fi, padding='same',
                         kernel_initializer='he_normal', activation='relu'))
    model.add(Conv2DTranspose(c, 9, strides=scale, padding='same',
                              kernel_initializer='he_normal'))
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def nsfsrcnn(x, d=56, s=12, m=4, scale=3, pos=1):
    """Build an FSRCNN model, but change deconv position.

    See https://arxiv.org/abs/1608.00367
    """
    model = Sequential()
    model.add(InputLayer(input_shape=x.shape[-3:]))
    c = x.shape[-1]
    f1 = [5, 1] + [3] * pos
    n1 = [d, s] + [s] * pos
    f2 = [3] * (m - pos - 1) + [1]
    n2 = [s] * (m - pos - 1) + [d]
    f3 = 9
    n3 = c
    for ni, fi in zip(n1, f1):
        model.add(Conv2D(ni, fi, padding='same',
                         kernel_initializer='he_normal', activation='relu'))
    model.add(Conv2DTranspose(s, 3, strides=scale, padding='same',
                              kernel_initializer='he_normal'))
    for ni, fi in zip(n2, f2):
        model.add(Conv2D(ni, fi, padding='same',
                         kernel_initializer='he_normal', activation='relu'))
    model.add(Conv2D(n3, f3, padding='same',
                         kernel_initializer='he_normal'))
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def espcn(x, f=[5, 3, 3], n=[64, 32], scale=3):
    """Build an ESPCN model.

    See https://arxiv.org/abs/1609.05158
    """
    assert len(f) == len(n) + 1
    model = Sequential()
    model.add(InputLayer(input_shape=x.shape[1:]))
    c = x.shape[-1]
    for ni, fi in zip(n, f):
        model.add(Conv2D(ni, fi, padding='same',
                         kernel_initializer='he_normal', activation='tanh'))
    model.add(Conv2D(c * scale ** 2, f[-1], padding='same',
                     kernel_initializer='he_normal'))
    model.add(Conv2DSubPixel(scale))
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def make_model_small(train_input, num_classes, weights_file=None):
    '''Return Cifar10 DL model with small number layers.'''
    model = Sequential()

    # model.add(KL.InputLayer(input_shape=inshape[1:]))
    if isinstance(train_input, tf.Tensor):
        model.add(KL.InputLayer(input_tensor=train_input))
    else:
        model.add(KL.InputLayer(input_shape=train_input))

    # if standardize:
    #     model.add(KL.Lambda(stand_img))

    model.add(KL.Conv2D(32, (3, 3), padding='same'))
    model.add(KL.Activation('relu'))
    model.add(KL.Flatten())
    # model.add(Dropout(0.5))
    model.add(KL.Dense(num_classes))
    model.add(KL.Activation('softmax'))

    if weights_file is not None and os.path.exists(weights_file):
        model.load_weights(weights_file)

    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def compute_output_shape(self, input_shape):
        return input_shape


# class LocalParam(InputLayer):

#     def __init__(self, shape, mult=1, my_initializer='RandomNormal', **kwargs):
#         super(LocalParam, self).__init__(input_shape=shape, **kwargs)       
       
#         # Create a trainable weight variable for this layer.
#         self.kernel = self.add_weight(name='kernel', 
#                                       shape=tuple(shape),
#                                       initializer=my_initializer,
#                                       trainable=True)
        
#         outputs = self._inbound_nodes[0].output_tensors
#         z = Input(tensor=K.expand_dims(self.kernel, 0)*mult)
#         if len(outputs) == 1:
#             self._inbound_nodes[0].output_tensors[0] = z
#         else:
#             self._inbound_nodes[0].output_tensors = z
      
#     def get_output(self):  # call() would force inputs
#             outputs = self._inbound_nodes[0].output_tensors
#             if len(outputs) == 1:
#                 return outputs[0]
#             else:
#                 return outputs 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def bicubic(x, scale=3):
    model = Sequential()
    model.add(InputLayer(input_shape=x.shape[-3:]))
    model.add(ImageRescale(scale, method=tf.image.ResizeMethod.BICUBIC))
    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def make_model(inshape, num_classes, weights_file=None):
    model = Sequential()
    model.add(KL.InputLayer(input_shape=inshape[1:]))
    # model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
    model.add(KL.Conv2D(32, (3, 3), padding='same'))
    model.add(KL.Activation('relu'))
    model.add(KL.Conv2D(32, (3, 3)))
    model.add(KL.Activation('relu'))
    model.add(KL.MaxPooling2D(pool_size=(2, 2)))
    model.add(KL.Dropout(0.25))

    model.add(KL.Conv2D(64, (3, 3), padding='same'))
    model.add(KL.Activation('relu'))
    model.add(KL.Conv2D(64, (3, 3)))
    model.add(KL.Activation('relu'))
    model.add(KL.MaxPooling2D(pool_size=(2, 2)))
    model.add(KL.Dropout(0.25))

    model.add(KL.Flatten())
    model.add(KL.Dense(512))
    model.add(KL.Activation('relu'))
    model.add(KL.Dropout(0.5))
    model.add(KL.Dense(num_classes))
    model.add(KL.Activation('softmax'))

    if weights_file is not None and os.path.exists(weights_file):
        model.load_weights(weights_file)

    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def make_model(x_train_input, nclasses):
    '''Non-functional model definition.'''
    model = Sequential()
    model.add(KL.InputLayer(input_tensor=x_train_input))
    ll = cnn_layers_list(nclasses)
    for il in ll:
        model.add(il)

    return model 

# 需要导入模块: from keras import layers [as 别名]
# 或者: from keras.layers import InputLayer [as 别名]
def make_model_full(train_input, num_classes, weights_file=None):
    '''Return Cifar10 DL model with many layers.

    :param train_input: Either a tf.Tensor input placeholder/pipeline, or a
        tuple input shape.
    '''
    model = Sequential()

    # model.add(KL.InputLayer(input_shape=inshape[1:]))
    if isinstance(train_input, tf.Tensor):
        model.add(KL.InputLayer(input_tensor=train_input))
    else:
        model.add(KL.InputLayer(input_shape=train_input))

    # if standardize:
    #     model.add(KL.Lambda(stand_img))

    model.add(KL.Conv2D(32, (3, 3), padding='same'))
    model.add(KL.Activation('relu'))
    model.add(KL.Conv2D(32, (3, 3)))
    model.add(KL.Activation('relu'))
    model.add(KL.MaxPooling2D(pool_size=(2, 2)))
    model.add(KL.Dropout(0.25))

    model.add(KL.Conv2D(64, (3, 3), padding='same'))
    model.add(KL.Activation('relu'))
    model.add(KL.Conv2D(64, (3, 3)))
    model.add(KL.Activation('relu'))
    model.add(KL.MaxPooling2D(pool_size=(2, 2)))
    model.add(KL.Dropout(0.25))

    model.add(KL.Flatten())
    model.add(KL.Dense(512))
    model.add(KL.Activation('relu'))
    model.add(KL.Dropout(0.5))
    model.add(KL.Dense(num_classes))
    model.add(KL.Activation('softmax'))

    if weights_file is not None and os.path.exists(weights_file):
        model.load_weights(weights_file)

    return model