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.

TDA2EVM5777: [TDA2x] Importing caffe-jacinto-model to TIDL

Part Number: TDA2EVM5777

Hello,

 

My customer is trying to run TIDL test application on TDA2. They are using TIDL 01.01.03.00 in PROCESSOR SDK VISION 03.07.00.00.

 

(1)They want to import “ssd768x320_ds_PSP_dsFac_32_hdDS8_0” from below link.

https://git.ti.com/cgit/jacinto-ai-devkit/caffe-jacinto-models/tree/trained/object_detection/voc0712/JDetNet

We can find deploy.prottxt only in directory “test_quantize”. Can we use it for importing the network to TIDL?

(2)After importing the network by step (1), they compared the result with JDetNet structure on Web. It looks like there are some difference in network structure between them.
Example:

[Layer #]     [Original network]    [Imported network]
Layer No.8      Pooling                Convolution
Layer No.10     Convolution            Pooling

We also see the difference in parameter values. Please find attachment for details.
Could you please let us know the reason of the difference?
Do we need to do anything for that?

TIDL_network_data.xlsx 

 

 Best regards,

-Shibata