Quantization-aware pytorch model convert tflite

[jiesonshan]

when using converter.convert()

File "/home/shanshaojie/project/TinyNeuralNetwork/tinynn/converter/base.py", line 356, in convert
self.init_jit_graph()
File "/home/shanshaojie/project/TinyNeuralNetwork/tinynn/converter/base.py", line 143, in init_jit_graph
script = torch.jit.trace(self.model, self.dummy_input)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 742, in trace
_module_class,
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 928, in trace_module
module = make_module(mod, _module_class, _compilation_unit)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 560, in make_module
return _module_class(mod, _compilation_unit=_compilation_unit)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 1040, in init
submodule, TracedModule, _compilation_unit=None
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 560, in make_module
return _module_class(mod, _compilation_unit=_compilation_unit)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 1040, in init
submodule, TracedModule, _compilation_unit=None
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 560, in make_module
return _module_class(mod, _compilation_unit=_compilation_unit)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 1040, in init
submodule, TracedModule, _compilation_unit=None
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/jit/_trace.py", line 549, in make_module
elif torch._jit_internal.module_has_exports(mod):
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/_jit_internal.py", line 505, in module_has_exports
item = getattr(mod, name)
File "/home/shanshaojie/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 779, in getattr
type(self).name, name))
torch.nn.modules.module.ModuleAttributeError: 'ConvModule' object has no attribute 'norm'
How to debug the problem? thanks

[peterjc123]

@jiesonshan It means that your model cannot go through torch.jit.trace. Please search for the keyword norm in the class ConvModule at your side.

[jiesonshan]

@peterjc123 thank you，the problem has been solved by modified ConvModule‘s norm method; but It may be an upstream bug from PyTorch, which refers to pytorch/pytorch#50680

[peterjc123]

I'm glad that you got it resolved. And thanks for the reference to the upstream bug report. But unluckily, there's not much we can help here.