Cannot load keras model with custom metric

Question

Hi I am trying to make a super resolution model on keras.

I am referring to https://github.com/titu1994/Image-Super-Resolution.

But after I compile and save a new model, when I load the model, the metric error is occurred

    Traceback (most recent call last):
  File "autoencoder2.py", line 56, in <module>
    load_model("./ani.model")
  File "/home/simmani91/anaconda2/lib/python2.7/site-packages/keras/models.py", line 155, in load_model
    sample_weight_mode=sample_weight_mode)
  File "/home/simmani91/anaconda2/lib/python2.7/site-packages/keras/engine/training.py", line 665, in compile
    metric_fn = metrics_module.get(metric)
  File "/home/simmani91/anaconda2/lib/python2.7/site-packages/keras/metrics.py", line 84, in get
    return get_from_module(identifier, globals(), 'metric')
  File "/home/simmani91/anaconda2/lib/python2.7/site-packages/keras/utils/generic_utils.py", line 14, in get_from_module
    str(identifier))
Exception: Invalid metric: PSNRLoss

and here is my code for metric(PSNRLoss), create model, execution

def PSNRLoss(y_true, y_pred):
    return -10. * np.log10(K.mean(K.square(y_pred - y_true)))

def create_model():
    shape = (360,640,3)
    input_img = Input(shape=shape)

    x = Convolution2D(64, shape[0],shape[1], activation='relu', border_mode='same', name='level1')(input_img)
    x = Convolution2D(32,shape[0],shape[1],  activation='relu', border_mode='same', name='level2')(x)

    out = Convolution2D(3, shape[0],shape[1],  border_mode='same', name='output')(x)

    model = Model(input_img, out)
    #model.compile(optimizer='adadelta', loss='binary_crossentropy')
    adam = optimizers.Adam(lr=1e-3)
    model.compile(optimizer=adam, loss='mse', metrics=[PSNRLoss])

    return model

path = "./picture/"

if not os.path.exists("./ani.model"):
    ani_model =  create_model()
    ani_model.save("./ani.model")

load_model("./ani.model")

Is there any way to load a model with PSNR metric?

Thank you for reading.

Answer 1

Load the model with load_model("ani.model", custom_objects={"PSNRLoss": PSNRLoss}) instead.