Replace all lambda functions with custom keras layers about onnx2keras

[ibadr]

Revisiting this, since one of the main use cases of onnx2keras for our group is to go PyTorch/CoreML -> ONNX -> Keras -> Tensorflow.js. However, the latter will not be able to run Python Lambda functions. What would you recommend in order to be able to avoid Lambda functions altogether?

[pedrofrodenas]

In my case a had a problem with the Clip layer, I realized that Cliping equals applying a Relu activation function so I replace in operation_layers.py in line 37 the following:

    relu_layer = keras.layers.ReLU(max_value=ensure_numpy_type(layers[node.input[2]]).astype(int))

    # def target_layer(x, vmin=0, vmax=ensure_numpy_type(layers[node.input[2]]).astype(int)):
    #     import tensorflow as tf
    #     return tf.clip_by_value(x, vmin, vmax)
    # layer = keras.layers.Lambda(target_layer, name=keras_name)
    # lambda_func[keras_name] = target_layer

    layers[node_name] = relu_layer(input_0)

That avoids using lambda layer