Traceback (most recent call last):
File "ultralytics/my/load_model.py", line 453, in <module>
amct.save_quant_retrain_model(
File "/root/.local/lib/python3.8/site-packages/amct_pytorch/common/utils/check_params.py", line 43, in wrapper
return func(*args, **kwargs)
File "/root/.local/lib/python3.8/site-packages/amct_pytorch/quantize_tool.py", line 459, in save_quant_retrain_model
raise RuntimeError(
RuntimeError: record_file is empty, no layers to be quantized. Please confirm the process of retrain quantification: whether the inference process is omitted after the training!
点赞
收藏
回复
分享
举报
已解决
问题描述：
对 Yolov8 模型使用 amct_pytorch 插件后，进行量化训练时不保存 record_file，在要保存量化模型时，会报如下错误：
Traceback (most recent call last): File "ultralytics/my/load_model.py", line 453, in <module> amct.save_quant_retrain_model( File "/root/.local/lib/python3.8/site-packages/amct_pytorch/common/utils/check_params.py", line 43, in wrapper return func(*args, **kwargs) File "/root/.local/lib/python3.8/site-packages/amct_pytorch/quantize_tool.py", line 459, in save_quant_retrain_model raise RuntimeError( RuntimeError: record_file is empty, no layers to be quantized. Please confirm the process of retrain quantification: whether the inference process is omitted after the training!Cann 版本 6.0.1， amct_pytorch 版本 0.16.1