On the edge Deep Learning with the Neural Processing Unit by i.MX 8M Plus NXP

Pubblicato il

Being an Avnet Silica partner, Deep Vision Consulting was asked to test the NPU (Neural Processing Unit) of the i.MX 8M Plus by NXP Semiconductors, before its official launch scheduled in March at embedded world Exhibition&Conference 2021. Well, our team stressed the NPU with some really challenging deep learning tasks for computer vision and the experience was really amazing! In case on-the-edge […]

Deep Vision at the Avnet Deep Learning workshop in Bologna

Pubblicato il

At the Deep Learning workshop in Bologna, organized by Avnet, Deep Vision Consulting got the invitation to share to the passionate goup of attendees about its experience on #deepneuralnetworks and #edgecomputing, in particular on running custom/optimized DNNs on Xilinx #ultrascale+. Thanks to Mauro Ferloni, Stefano Tabanelli and all the group from Avnet for the great […]

STAND PRESSO SPS IPC DRIVES, PARMA, 2018

Pubblicato il

Un ringraziamento speciale al nostro partner e fornitore Advanced Technologies, che ha dato a Deep Vision Consulting l’opportunità di avere un angolo espositivo presso il loro stupendo stand fieristico a SPS IPC Drives, edizione italiana, la grande fiera dell’automazione tenuta alle Fiere di Parma, 22-24 Maggio 2018. Abbiamo mostrato alcuni esempi di tecnologie embedded: stima della […]

MULTIPLE OBJECT TRACKING WITH MHT

Pubblicato il

In last couple of years we had the chance to work quite a lot on Multiple Object Tracking, a very hot topic in research; differently from many other tasks in computer vision, deep learning here is (still) not the definitive technology for solving the task. However the debate is quite open. Please check MOT challenge […]

FROM KERAS TO CAFFE

Pubblicato il

Keras is a great tool to train deep learning models, but when it comes to deploy a trained model on FPGA, Caffe models are still the de-facto standard. Unfortunately, one cannot simply take a model trained with keras and import it into Caffe. The reason is twofold: first, Caffe doesn’t offer any import functions from […]