Part Number: TDA2EVM5777
Hi Everyone,
Could any one please help me in understanding what is the Machine learning framework used by the Linux TIDL image classification demo.
This thread has been locked.
If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.
Part Number: TDA2EVM5777
Hi Everyone,
Could any one please help me in understanding what is the Machine learning framework used by the Linux TIDL image classification demo.
Hi,
The image classification models in the demo are trained using Caffe-Jacinto framework and they are available in the below GitHub repository.
https://github.com/tidsp/caffe-jacinto-models/tree/caffe-0.16/trained/image_classification/imagenet_jacintonet11v2
Thanks,
Praveen
Hi Praveen,
Currently I am using psdk_rtos_auto_j7_06_02_00_21 package, Could you please located the where to refer image classification demo using cafe jacinto and also provide me a documentation link to understand it better if you have some.
Hi,
Do you want demos for TDA2 or TDA4 device because thread subject says TDA2 but you are using J7 (TDA4) package ?
Thanks,
Praveen
Hi Praveen,
Thanks for the reply.
I want a TIDL image classification demo for TDA4 J7, Did you have any demo source and build instructions available with you? Currently I could not able to understand the demo source structure but only be able to run the image classification demo over Linux boot and invoking the demo using a the script. But could not able to understand what is the deep learning framework model used i.e; caffe jacinto or tensor flow, how it is getting imported etc.
The main requirement of mine to develop and train a deep learning model using TIDL which senses numbers from 0 to 100.