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.
Hi:
In case of AVP version1, jpsdNet and jsegNet each one works. Can i get the jpsdNet tarining code ?
If possible, I'll try to train jpsdNet model again. (Transfer learning or fine-tuning for my dataset.)
Regards
Gong
Hi,
The model is based on Mobilenet v1 + SSD. The technique has been published at
https://ieeexplore.ieee.org/document/9012933
We can provide training code. Can you please let us know more about your targeted application which you are planning on TDA4x ? Any FAE you are in contact with ?
Regards
Deepak Poddar
Hi:
We are trying to port the parking space detection to TDA4. I saw in this post(https://e2e.ti.com/support/processors/f/processors-forum/935322/tda4vm-can-i-get-pre-trained-not-imported-jpsdnet-model) that you said that the training code will be released in the first quarter of this year, right?
Regards
Gong
Hi,
we are delayed in making the release of training framework. We will make release in 3rd Quarter.
Regards
Deepak Poddar
Hi,
we have released the training code with pretrained weights at
https://git.ti.com/cgit/jacinto-ai/pytorch-ssds-keypoints/about/
Regards
Deepak Poddar
What a coincidence, I just realized the key point detection based on ssd today, thank you for your work
Hi,
Which labeling software is used to make the data set in parking space recognition?
Regards
Gong
Hi,
You may use cityscapes labelling tool with minor modifications, or any other labelling tool which are used in key point labelling.
Regards
Deepak Poddar