-
Notifications
You must be signed in to change notification settings - Fork 220
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
The problem about using RECORDER in dev1.x (RecorderManager) #433
Comments
Hi @cape-zck ! Thank you for your issue. While the |
* [refactor][API2.0] Add onnx export and jit trace (open-mmlab#419) * first commit * add async call * add new api onnx export and jit trace * add decorator * fix ci * fix torchscript ci * fix loader * better pipemanager * remove comment, better import * add kwargs * remove comment * better pipeline manager * remove print * [Refactor][API2.0] Api partition calibration (open-mmlab#433) * first commit * add async call * add new api onnx export and jit trace * add decorator * fix ci * fix torchscript ci * fix loader * better pipemanager * remove comment, better import * add partition * move calibration * Better create_calib_table * better deploy * add kwargs * remove comment * better pipeline manager * rename api, remove reduant variable, and misc * [Refactor][API2.0] Api ncnn openvino (open-mmlab#435) * first commit * add async call * add new api onnx export and jit trace * add decorator * fix ci * fix torchscript ci * fix loader * better pipemanager * remove comment, better import * add ncnn api * finish ncnn api * add openvino support * add kwargs * remove comment * better pipeline manager * merge fix * merge util and onnx2ncnn * fix docstring * [Refactor][API2.0] API for TensorRT (open-mmlab#519) * first commit * add async call * add new api onnx export and jit trace * add decorator * fix ci * fix torchscript ci * fix loader * better pipemanager * remove comment, better import * add partition * move calibration * Better create_calib_table * better deploy * add kwargs * remove comment * Add tensorrt API * better pipeline manager * add tensorrt new api * remove print * rename api, remove reduant variable, and misc * add docstring * [Refactor][API2.0] Api ppl other (open-mmlab#528) * first commit * add async call * add new api onnx export and jit trace * add decorator * fix ci * fix torchscript ci * fix loader * better pipemanager * remove comment, better import * add kwargs * Add new APIS for pplnn sdk and misc * remove comment * better pipeline manager * merge fix * update tools/onnx2pplnn.py * rename function
Could you help me check #636 |
Thanks to the MMrazor team contribution, Now I am learning the use of MMrazor dev1.x about the RECORDER moudle, but I ran into a couple of problems.
1.I find no mmrazor.core in dev1.x. however,I find the module such as MethodOutputsRecorder, RecorderManager and so on in mmrazor.models.task_modules, this problem seems to have been solved.
2.But when I test the demo about RecorderManager, I found that if I tried to use ModuleOutputs and MethodOutputs in RecorderManager at the same time, the forward process would seem to run twice, and output MethodOutputs would report an out-of-range error. But if the Method(toy_func) isn’t in the same python file, this error doesn't seem to happen.
For example:
But when I remove the MethodOutputs, everything seemed normal again.
The text was updated successfully, but these errors were encountered: