Pytorch equivalent of activation=Linear from Keras

Mukesh1729 · November 20, 2021, 4:42pm

What is the equivalent of the activation= linear in Pytorchfrom keras? Thanks

x_out = Conv2DTranspose(output_channels, kernel_size=3, strides=2, padding="same", activation="linear", kernel_initializer="glorot_normal")

Eta_C · November 22, 2021, 6:34am

It seems that activation.linear means forwarding without activation?

github.com

keras-team/keras/blob/5c4074a820a08505cf87562f60d21adfdc2dfb05/keras/activations.py#L459-L477

    
      
          @keras_export('keras.activations.linear')
          @tf.__internal__.dispatch.add_dispatch_support
          def linear(x):
            """Linear activation function (pass-through).
          
          
  For example:
          
          
  >>> a = tf.constant([-3.0,-1.0, 0.0,1.0,3.0], dtype = tf.float32)
            >>> b = tf.keras.activations.linear(a)
            >>> b.numpy()
            array([-3., -1.,  0.,  1.,  3.], dtype=float32)
          
          
  Args:
                x: Input tensor.
          
          
  Returns:
                The input, unmodified.
            """
            return x

Mukesh1729 · November 22, 2021, 7:33am

Hey Eta_C, thanks for cofirming.