search

HSqure / ultralytics-pt-yolov3-vitis-ai-edge

This demo is only used for inference testing of Vitis AI v1.4 and quantitative compilation of DPU. It is compatible with the training results of v9.5.0 version of ultramatics (it needs to use the model saving method of Python 1.4 version)
GNU General Public License v3.0
6 stars 3 forks source link

Save model #2

Open masrourabdou opened 2 years ago

masrourabdou commented 2 years ago

Hello Sir , Could you please let me know what's best_quant mean ?

    torch.save(ckpt, best)
    torch.save(model, best_quant, _use_new_zipfile_serialization=False)
HSqure commented 2 years ago

Hello Sir , Could you please let me know what's best_quant mean ?

    torch.save(ckpt, best)
    torch.save(model, best_quant, _use_new_zipfile_serialization=False)

Hi, BEST means the best AP from all step and QUANT means that it's for quantization process.

feng040107 commented 10 months ago

hello sir , May I ask what else needs to be modified during training?

image

feng040107 commented 10 months ago

Please solve the following problems image