[Bug] (suggested fix) `mmrazor.models.algorithms.mm_architecture.MMArchitectureQuant.get_deploy_model()` fails if `predict` mode lacks nodes from the `model.quantizer.tracer.skipped_methods` configuration, but the architecture `quantizer.prepare(fp32_model)` has these nodes. about mmrazor HOT 4 OPEN

Looking more into it, it seems the tensor mode fix is correct, but the next error has to do with the model having some modules that can't be fake quantized modules like Hard Sigmoid, which are defined in torch.ao.quantization.qconfig_mapping._FIXED_QPARAMS_OP_TO_OBSERVER.

from mmrazor.

Hi! How did you use the output of the method get_deploy_model of MMArchitectureQuant to then convert the model to onnx?

I'm trying to export a quantized model using PyTorch 1.13.1 and using MMDeploy for_mmrazor branch didn't work for me... So, looking at MMRazor, I have created a hook called at the end of the training, that gets the output of get_deploy_model (an torch ObservedGraphModule) and passes it to torch.onnx.export with some arguments.

I'm not sure what I'm doing is right, but I also don't understand why using MMDeploy if MMRazor provides quantizers with onnx_export methods...

EDIT: I have an exported onnx file but it seems that I only have quantized weights and not activations

from mmrazor.

I used a merge of the most recent mmdeploy with the for_mmrazor branch.

from mmrazor.

Which script(s) are you using? What is the purpose of having a get_deploy_model method in MMRazor that returns an GraphModule and a deploy.py script in MMDeploy that takes a checkpoint file as input? I'm confused. Moreover, we already have an export_onnx method in TorchNativeQuantizer of MMRazor and it seems that the get_deploy_model method is never called in the QAT training of MMRazor.

from mmrazor.