79 results
- Go to itemExponential linear units were introduced to alleviate the disadvantages of ReLU and LeakyReLU units, namely to push the mean acti…0
- Go to itemA leaky ReLU is a rectified linear unit (ReLU) with a slope in the negative part of its input space. The motivation for leaky ReL…0
- Go to itemLike the leaky ReLU, the parametric ReLU introduces a slope in the negative part of the input space to improve learning dynamics …0
- Go to itemLike the leaky ReLU, the parametric ReLU introduces a slope in the negative part of the input space to improve learning dynamics …0
- Go to itemThe softmax function is commonly used as the last layer in a classification network. It transforms an unconstrained n-dimensional…0
- Go to itemSimilar to ordinary ReLUs but shifted by theta. f(x) = x for x > theta, f(x) = 0 otherwise . Corresponds to the Keras Thresholded…0
- Go to itemThis layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …0
- Go to itemThis layer creates a convolution kernel that is convolved with the layer input over a single dimension. Corresponds to the Keras …0
- Go to itemThis layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…0
- Go to itemThe need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …0
- Go to itemThe need for transposed convolutions generally arises from the desire to use a transformation going in the opposite direction of …0
- Go to itemRepeats the layer input element-wise in a single dimension. Corresponds to the Keras Upsampling 1D Layer .0
- Go to itemRepeats the rows and columns of the layer input. Corresponds to the Keras Upsampling 2D Layer .0
- Go to itemRepeats the layer input element-wise in three dimension. Corresponds to the Keras Upsampling 3D Layer .0
- Go to itemThis layer crops the layer input in two dimensions. Corresponds to the Keras Cropping 2D Layer .0
- Go to itemThis layer crops the layer input in three dimensions. Corresponds to the Keras Cropping 3D Layer .0
- Go to itemThis layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…0
- Go to itemThis layer performs convolution in a single dimension with a factorization of the convolution kernel into two smaller kernels. Co…0
- Go to itemThis layer performs convolution in two dimensions with a factorization of the convolution kernel into two smaller kernels. Corres…0
- Go to itemThis layer creates a convolution kernel that is convolved with the layer input over two dimensions. Corresponds to the Keras Conv…0