Texas Instruments Corporation

Pramod Kumar Swami

Soyeb Noormohammed Nagori

Deepak Kumar Poddar

Manu Mathew

Kumar Arrakutti Desappan

Arun Shankar Kudana

Shyam Jagannathan

Prashanth Ramanathpur Viswanath

Mihir Narendra Mody

Uday Pudipeddi Kiran

Kumar Desappan

Anshu Jain

Timothy David Anderson

Abhijeet Ashok Chachad

David Matthew Thompson

Naveen Bhoria

Hrushikesh Tukaram Garud

Kedar Satish Chitnis

Manoj Koul

Anurag Mithalal Jain

Neelima Muralidharan

Debapriya Maji

Venugopala Krishna Madumbu

Praveen Eppa

Desappan Kumar

Minhua Zhou

Mehmet Umut Demircin

Osman Gokhan Sezer

David E Smith

Victor Cheng

Rishabh Garg

David Gottardo

Uday Kiran Pudipeddi

Jacques Michel Bride

David Smith

Raghavendra Kudva

Techniques for executing machine learning (ML) models including receiving an indication to run an ML model on a processing core; receiving a static memory allocation for running the ML model on the processing core; determining that a layer of the ML model uses more memory than the static memory allocated; transmitting, to a shared memory, a memory request for blocks of the shared memory; receiving an allocation of the requested blocks; running the layer of the ML model using the static memory and the range of memory addresses; and outputting results of running the layer of the ML model.

Memory sharing for machine learning processing

A hardware accelerator is configured to perform matrix multiplication and/or additional operations to optimize keypoint matching. A sum of squared error (SSE) calculation may be determined by utilizing the hardware accelerator to perform matrix multiplication to obtain a cost matrix for two sets of keypoint descriptors from two images. The hardware accelerator may determine a best cost calculation for each keypoint in each direction, which is utilized to perform keypoint matching.

Two-way descriptor matching on deep learning accelerator

A method for multi-label image classification in a convolutional neural network (CNN) is provided that includes forming a composite image from a plurality of clipped images, and processing the composite image by the CNN to generate a probability vector for each clipped image of the plurality of clipped images, wherein a length of a probability vector is equal to a number of classes the CNN is designed to classify.

Multi-label image classification in a deep learning network

This invention predicts that intra mode prediction is more effective for the macroblocks where motion estimation in inter mode prediction fails. This failure is indicated by a large value of the inter mode SAD. This invention performs intra mode prediction for only macro blocks have larger inter mode SADs. The definition of a large inter mode SAD differs for different content. This invention compares the inter mode SAD of a current macroblock with an adaptive threshold. This adaptive threshold depends on the average and variance of the SADs of the previous predicted frame. An adaptive threshold is calculated for each new predictive frame.

Intra/inter mode decision for predictive frame encoding

In described examples of a method for quantizing data for a convolutional neural network (CNN) is provided. A set of data is received and quantized the using a power-of-2 parametric activation (PACT2) function. The PACT2 function arranges the set of data as a histogram and discards a portion of the data corresponding to a tail of the histogram to form a remaining set of data. A clipping value is determined by expanding the remaining set of data to a nearest power of two value. The set of data is then quantized using the clipping value. With PACT2, a model can be quantized either using post training quantization or using quantization aware training. PACT2 helps a quantized model to achieve close accuracy compared to the corresponding floating-point model.

Parametric power-of-2 clipping activations for quantization for convolutional neural networks

An apparatus includes first CPU and second CPU cores, a L1 cache subsystem coupled to the first CPU core and comprising a L1 controller, and a L2 cache subsystem coupled to the L1 cache subsystem and to the second CPU core. The L2 cache subsystem includes a L2 memory and a L2 controller configured to operate in an aliased mode in response to a value in a memory map control register being asserted. In the aliased mode, the L2 controller receives a first request from the first CPU core directed to a virtual address in the L2 memory, receives a second request from the second CPU core directed to the virtual address in the L2 memory, directs the first request to a physical address A in the L2 memory, and directs the second request to a physical address B in the L2 memory.

Aliased mode for cache controller

A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.

Feature point identification in sparse optical flow based tracking in a computer vision system

A method for convolution in a convolutional neural network (CNN) is provided that includes accessing a coefficient value of a filter corresponding to an input feature map of a convolution layer of the CNN, and performing a block multiply accumulation operation on a block of data elements of the input feature map, the block of data elements corresponding to the coefficient value, wherein, for each data element of the block of data elements, a value of the data element is multiplied by the coefficient value and a result of the multiply is added to a corresponding data element in a corresponding output block of data elements comprised in an output feature map.

Reduced complexity convolution for convolutional neural networks

Several methods and systems for facilitating multimedia data encoding are disclosed. In an embodiment, a plurality of picture buffers associated with multimedia data are received in an order of capture associated with the plurality of picture buffers. Buffer information is configured for each picture buffer from among the plurality of picture buffers comprising at least one of a metadata associated with the corresponding picture buffer and one or more encoding parameters for the corresponding picture buffer. A provision of picture buffers in an order of encoding is facilitated based on the configured buffer information.

Methods and systems for facilitating multimedia data encoding using storage buffers

Several techniques aimed at reducing computational complexity when encoding uses bi-predictively encoded frames (B-frames) are implemented in a video encoder. In an embodiment, B-frames are not used as reference frames for encoding P-frames and other B-frames. Non-use of B-frames allows a de-blocking filter used in the video encoder to be switched off when reconstructing encoded B-frames, and use of a lower complexity filter for fractional-resolution motion search for B-frames. In another embodiment, cost functions used in motion estimation for B-frames are simplified to reduce computational complexity. In one more embodiment, fractional pixel refinement in motion search for B-frames is simplified. In yet another embodiment, predictors used in motion estimation for a macro-block in a P-frame are selected from a B-frame that uses a same reference frame as the P-frame.

Reducing computational complexity when video encoding uses bi-predictively encoded frames

A matching accelerator in the form of a hardware accelerator configured to perform matrix multiplication and/or additional operations is used to optimize keypoint matching. An SSE calculation may be determined by utilizing the matching accelerator to perform matrix multiplication to obtain a cost matrix for two sets of keypoint descriptors from two images. The hardware accelerator may determine a best cost calculation for each keypoint in each direction, which is utilized to perform keypoint matching.

The disclosure provides a noise filter. The noise filter includes a motion estimation (ME) engine. The ME receives a current frame and a reference frame. The current frame comprising a current block and the reference frame includes a plurality of reference blocks. The ME engine generates final motion vectors. The current block comprises a plurality of current pixels. A motion compensation unit generates a motion compensated block based on the final motion vectors and the reference frame. The motion compensated block includes a plurality of motion compensated pixels. A weighted average filter multiplies each current pixel of the plurality of current pixels and a corresponding motion compensated pixel of the plurality of motion compensated pixels with a first weight and a second weight respectively. The weighted average filter generates a filtered block. A blockiness removal unit is coupled to the weighted average filter and removes artifacts in the filtered block.

Method and apparatus for noise reduction in video systems

Techniques including receiving a first set of values for processing by a machine learning (ML) network, storing a first portion of the first set of values in an on-chip memory, processing the first portion of the first set of values in a first layer of the ML network to generate a second portion of a second set of values, overwriting the stored first portion with the generated second portion, processing the second portion in a second layer of the ML network to generate a third portion of a third set of values, storing the third portion, repeating the steps of storing the first portion, processing the first portion, overwriting the stored first portion, processing the second portion, and storing the third portion for a fourth portion of the first set of values until all portions of the first set of values are processed to generate the third set of values.

Super-tiling in neural network processing to enable analytics at lower memory speed

A method for video object detection includes detecting an object in a first video frame, and selecting a first interest point and a second interest point of the object. The first interest point is in a first region of interest located at a first corner of a box surrounding the object. The second interest point is in a second region of interest located at a second corner of the box. The second corner is diagonally opposite the first corner. A first optical flow of the first interest point and a second optical flow of the second interest point are determined. A location of the object in a second video frame is estimated by determining, in the second video frame, a location of the first interest point based on the first optical flow and a location of the second interest point based on the second optical flow.

Growing community of inventors

Bengaluru, India

Pramod Kumar Swami