Method or an apparatus implementing a neural network-based processing at low complexity

A computer-implemented method, comprising:

• obtaining a tensor of input data representative of data samples of an image block;
• applying a neural network-based processing to the tensor of input data to generate a tensor of output data;
• and
• encoding the image block based on the tensor of output data;
• wherein the neural network-based processing comprises a plurality of processing layers, wherein each of the plurality of processing layers generates an intermediate tensor, wherein at least one of the plurality of processing layers is represented as a tensor product between the tensor of input data and a weight tensor, and wherein at least one of the plurality of processing layers is represented as an addition of a bias tensor and is fused with the at least one of the plurality of processing layer representing the tensor product;
• wherein a scaling factor of a quantized representation of tensor of input data, a scaling factor of a quantized representation of the weight tensor, a scaling factor of a quantized representation of the bias tensor, a scaling factor of a quantized representation of an intermediate tensor, and a scaling factor of a quantized representation of the tensor of output data are powers of two, and a quantized representation of a tensor being obtained by a shift according to an exponent of a respective power of two scaling factor;
• and
• wherein the fusion of the at least one processing layer representing the addition of the bias tensor with the at least one processing layer representing the tensor product involves a single combined bit-shifting operation for scaling a result of the tensor product with the scaling factor of the quantized representation of the bias tensor.

An apparatus comprising a memory and one or more processors, wherein the one or more processors are configured to:

• obtain a tensor of input data representative of coded data samples of an image block;
• apply a neural network-based processing to the tensor of input data to generate a tensor of output data;
• and
• decode the image block based on the tensor of output data;
• wherein the neural network-based processing comprises a plurality of processing layers, wherein each of the plurality of processing layers generates an intermediate tensor, wherein at least one of the plurality of processing layers is represented as a tensor product between the tensor of input data and a weight tensor, and wherein at least one of the plurality of processing layers is represented as an addition of a bias tensor and is fused with the at least one of the plurality of processing layer representing the tensor product;
• wherein a scaling factor of a quantized representation of tensor of input data, a scaling factor of a quantized representation of the weight tensor, a scaling factor of a quantized representation of the bias tensor, a scaling factor of a quantized representation of an intermediate tensor, and a scaling factor of a quantized representation of the tensor of output data are powers of two, a quantized representation of a tensor being obtained by a shift according to an exponent of a respective power of two scaling factor;
• and
• wherein the fusion of the at least one processing layer representing the addition of the bias tensor with the at least one processing layer representing the tensor product involves a single combined bit-shifting operation for scaling a result of the tensor product with the scaling factor of the quantized representation of the bias tensor.

An apparatus comprising a memory and one or more processors, wherein the one or more processors are configured to:

• obtain a tensor of input data representative of data samples of an image block;
• apply a neural network-based processing to the tensor of input data to generate a tensor of output data;
• and
• encode the image block based on the tensor of output data;
• wherein the neural network-based processing comprises a plurality of processing layers, wherein each of the plurality of processing layers generates an intermediate tensor, wherein at least one of the plurality of processing layers is represented as a tensor product between the tensor of input data and a weight tensor, and wherein at least one of the plurality of processing layers is represented as an addition of a bias tensor and is fused with the at least one of the plurality of processing layer representing the tensor product;
• wherein a scaling factor of a quantized representation of tensor of input data, a scaling factor of a quantized representation of the weight tensor, a scaling factor of a quantized representation of the bias tensor, a scaling factor of a quantized representation of an intermediate tensor, and a scaling factor of a quantized representation of the tensor of output data are powers of two, a quantized representation of a tensor being obtained by a shift according to an exponent of a respective power of two scaling factor;
• and
• wherein the fusion of the at least one processing layer representing the addition of the bias tensor with the at least one processing layer representing the tensor product involves a single combined bit-shifting operation for scaling a result of the tensor product with the scaling factor of the quantized representation of the bias tensor.