vanjuan339 opened a new issue, #17705: URL: https://github.com/apache/tvm/issues/17705
Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion, roadmaps, and bug tracking. You are always welcomed to post on the forum first :smile_cat: Issues that are inactive for a period of time may get closed. We adopt this policy so that we won't lose track of actionable issues that may fall at the bottom of the pile. Feel free to reopen a new one if you feel there is an additional problem that needs attention when an old one gets closed. ### Expected behavior Want to quantize a custom model ### Actual behavior Calling interface：mod = relay.quantize.quantize(mod, params=params, dataset=dataset) The following error occurs： 3: tvm::relay::TypeInferencer::Infer(tvm::GlobalVar, tvm::relay::Function) 2: tvm::relay::TypeSolver::Solve() 1:tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<bool (tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>::AssignTypedLambda<bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>(bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&))::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*) 0: tvm::relay::quantize::SimulatedQuantizeRel(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&) File "/tvm/src/relay/quantize/quantize.cc", line 52 InternalError: Check failed: data->shape.size() != 0 (0 vs. 0) : Input shape cannot be empty ### Environment x86_64 GNU/Linux tvm-0.19.0-py3.9 ### Steps to reproduce ''' onnx_model_path = "./model.onnx" onnx_model = onnx.load(onnx_model_path) input_name = "image" input_shape = (1,3,32,900) mod, params = relay.frontend.from_onnx(onnx_model, shape={input_name:input_shape}) dataset = [{"image": np.random.randn(1,3,32,900).astype("float32")} for _ in range(100)] with tvm.transform.PassContext(opt_level=3): with relay.quantize.qconfig( calibrate_mode="kl_divergence", weight_scale="max", skip_conv_layers=[], skip_dense_layer=False ): quantized_mod = relay.quantize.quantize(mod, params, dataset=dataset) quantized_mod.show() ''' ### Triage Please refer to the list of label tags [here](https://github.com/apache/tvm/wiki/Issue-Triage-Labels) to find the relevant tags and add them below in a bullet format (example below). * needs-triage -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
