Hucley

about “ train_PQAN_pool2.prototxt"

3

1.The output of pool_s layer isn't used in the next, why? 2. In this prototxt, you choose the "pool2/3x3_s2" as the input of quality generation unit, which is the different...

Is the function "my_solver.snapshot('snapshot_path_and_name')" to save the "XXX.caffemodel.solverstate“ file? --then we try to recover the traing proicessing by using the function"caffe_solver.restore("XXX.caffemodel.solverstate") ,but there some errors: sgd_solver.cpp:316] Check failed: state.history_size() ==...

很优秀的一系列工作，不过没那么多A100卡，后续有相应的国产化项目或者branch嘛

### 问题确认 Search before asking - [X] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 使用paddle版本:(3.0版本训练异常）  docker镜像： registry.baidubce.com/device/paddle-npu:cann80RC1-ubuntu20-aarch64-gcc84-py310 训练状态：  使用多个版本yolo-seg均出现类似情况，希望能得到解决