Does TVM support importing TFLite models with dynamic shapes?
I have a DeepLabV3 model that causes TVM to crash when handling EXPAND_DIMS
:
TVMError:
---------------------------------------------------------------
An internal invariant was violated during the execution of TVM.
Please read TVM's error reporting guidelines.
More details can be found here: https://discuss.tvm.ai/t/error-reporting/7793.
---------------------------------------------------------------
Check failed: (false) is false: [12:18:44] /w/src/dmlc/tvm/src/relay/op/tensor/transform.cc:565:
---------------------------------------------------------------
An internal invariant was violated during the execution of TVM.
Please read TVM's error reporting guidelines.
More details can be found here: https://discuss.tvm.ai/t/error-reporting/7793.
---------------------------------------------------------------
Check failed: infer_idx < 0 (0 vs. 0) : One and only one dim can be inferred