Hello, i want to train a face detector caffe model, so i can use it in Deepstream. I’ve gathered a dataset based on open images dataset v4. Im trying to use the resnet.prototxt located in deepstream_sdk_v4.0.1_jetson/samples/models/Primary_Detector_Nano and the associated weights. My question is, what are the steps i shoul follow? Shoul i resize all of my images in my dataset in DIGITS? once i have the caffe model, can i use it directly in deepstream? do i have to generate a .engine model?
AastaLLL
2
Hi,
YES.
The model can be re-trained with DIGITS directly.
Thanks.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Use custom caffe model in Deepstream SDK | 1 | 1066 | September 16, 2019 | |
| How to train Deepstream resnet10.caffemodel in DIGITS | 8 | 2386 | November 28, 2019 | |
| Error trying to create engine from DIGIT trained model files | 19 | 1484 | December 16, 2019 | |
| import ResNet_18 DeepStream sample in DIGITS | 0 | 607 | June 15, 2018 | |
| About caffe model? | 2 | 498 | July 30, 2019 | |
| Running facenet caffe model | 1 | 1364 | September 19, 2019 | |
| How do I retrain "Primary_Detector_Nano" for my images | 3 | 524 | September 12, 2019 | |
| Port Resnet50.caffemodel and its prototxt to be used in Deepstream 5.0? | 5 | 728 | July 7, 2020 | |
| Deepstream: How to build a working model | 8 | 2800 | December 27, 2017 | |
| Port SSD caffemodel to Deepstream 5.0 | 3 | 447 | August 24, 2020 |