Closed mbencer closed 1 month ago
I fixed this issue like this.
It has a known issue. The created circle file contains two buffers with the same data becasue this PR just adds a new buffer without removing the existing buffer. However, it is a ONERT's problem. ONERT should not add a new operand if the data has not changed. Apart from this issue, when the tensor is added to a trainable graph, it should be created in a newly generated circle file.
Steps to reproduce:
Model: mobilenet v2 Train data: mobilenet data
Command:
Current state: The exception
Trainable tensor index is out of range
is called because ConstantInsertionPass called during trainable graph lowering change the operands values. In my mobilenet v2 caseConstantInsertionPass
is called forPad
operator. The new operand with value182
is created in trainable graph. This operand does NOT exist in the origin model loaded by CircleExporter.Ideas for fix:
updateWeight
??//cc @jyoungyun