Custom layer tensorflow gets error ‘customlayer’ object has no attribute ‘layers’-CodePudding

I’ve made a custom layer with the class method and when I’m trying to call the class it shows this error message :

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-143-9ad907fef5b1> in <module>
----> 1 model.layers()

AttributeError: 'lane_detection_network' object has no attribute 'layers'

the code is here:

class lane_detection_network(tf.Module):
    def __init__(self):
        super(lane_detection_network, self).__init__()

        self.resizing = resize_layer(3, 128)

        #feature extraction
        self.layer1 = hourglass_block(128, 128)
        self.layer2 = hourglass_block(128, 128)

    def call(self, inputs):
        #feature extraction
        out = self.resizing(inputs)
        result1, out = self.layer1(out)
        result2, out = self.layer2(out)      

        return [result1, result2]

CodePudding user response：

I believe this is because tf.Module is a very basic class - it does not have layers. Also, you have not explicitly set them.

Is there a reason you are not using Keras? Otherwise, this TF guide demonstrates exactly how to achieve what you want. Make sure you know the difference between a Layer and a Model and then it should be straightforward to get the desired result.