Skuldur / facenet-face-recognition

A face recognition demo performed by feeding images of faces recorded by a webcam into a trained FaceNet network to determine the identity of the face
386 stars 291 forks source link

Have to clear tensorflow graphs. #17

Open afghani-iitkgp opened 4 years ago

afghani-iitkgp commented 4 years ago
ValueError: Fetch argument <tf.Variable 'conv1/kernel:0' shape=(7, 7, 3, 64) dtype=float32_ref> cannot be interpreted as a Tensor.
(Tensor Tensor("conv1/kernel:0", shape=(7, 7, 3, 64), dtype=float32_ref) is not an element of this graph.)

I was using this model for face similarity project. But I did encounter above "ValueError". I overcame by clearing the session. My code is:

def faceRecoModel(input_shape):
    # Clear previous session
    K.clear_session()

    # Define the input as a tensor with shape input_shape
    X_input = Input(input_shape)

    # Zero-Padding
    X = ZeroPadding2D((3, 3))(X_input)
    .
    # First Block
    X = Conv2D(64, (7, 7), strides=(2, 2), name='conv1')(X)
    X = BatchNormalization(axis=1, name='bn1')(X)
    X = Activation('relu')(X)

    # Zero-Padding + MAXPOOL
    X = ZeroPadding2D((1, 1))(X)
    X = MaxPooling2D((3, 3), strides=2)(X)

    # Second Block
    X = Conv2D(64, (1, 1), strides=(1, 1), name='conv2')(X)
    X = BatchNormalization(axis=1, epsilon=0.00001, name='bn2')(X)
    X = Activation('relu')(X)

    # Zero-Padding + MAXPOOL
    X = ZeroPadding2D((1, 1))(X)

    # Third Block
    X = Conv2D(192, (3, 3), strides=(1, 1), name='conv3')(X)
    X = BatchNormalization(axis=1, epsilon=0.00001, name='bn3')(X)
    X = Activation('relu')(X)

    # Zero-Padding + MAXPOOL
    X = ZeroPadding2D((1, 1))(X)
    X = MaxPooling2D(pool_size=3, strides=2)(X)

    # Inception 1: a/b/c
    X = inception_block_1a(X)
    X = inception_block_1b(X)
    X = inception_block_1c(X)

    # Inception 2: a/b
    X = inception_block_2a(X)
    X = inception_block_2b(X)

    # Inception 3: a/b
    X = inception_block_3a(X)
    X = inception_block_3b(X)

    # Top layer
    X = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), data_format='channels_first')(X)
    X = Flatten()(X)
    X = Dense(128, name='dense_layer')(X)

    # L2 normalization
    X = Lambda(lambda x: K.l2_normalize(x, axis=1))(X)

    # Create model instance
    model = Model(inputs=X_input, outputs=X, name='FaceRecoModel')

    return model