The test will produce several error log like:
API Usage Error (Tensor slice_output_data_subgraph_4 has axis 3 with inherently negative length. Proven upper bound is -111894960. Network must have an instance where axis has non-negative length.)
, which is uninitialized memory issue due to TRT10 alias Dims to Dims64,
but TRT8 alias Dims to Dims32.
Reproduce
Run unittest test_trt_convert_strided_slice with TRT 10. It'll fail with high probability
這個commit 專注C++ TRT converter的改動,也就是現況正在應用的版本。
過去舊有的代碼,以int32_t寫死初始化的memset大小。造成TRT10介面更動時代碼無法自動適應。會因uninitialized memory造成random issue。
你的PR提交成功,感谢你对开源项目的贡献!
请关注后续CI自动化测试结果,详情请参考Paddle-CI手册。
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.
PR Category
Inference
PR Types
Bug fixes
Description
The test will produce several error log like: API Usage Error (Tensor slice_output_data_subgraph_4 has axis 3 with inherently negative length. Proven upper bound is -111894960. Network must have an instance where axis has non-negative length.)
, which is uninitialized memory issue due to TRT10 alias Dims to Dims64, but TRT8 alias Dims to Dims32.
Reproduce
Run unittest
test_trt_convert_strided_slice
with TRT 10. It'll fail with high probability這個commit 專注C++ TRT converter的改動,也就是現況正在應用的版本。 過去舊有的代碼,以
int32_t
寫死初始化的memset大小。造成TRT10介面更動時代碼無法自動適應。會因uninitialized memory造成random issue。In short,此commit修正兩個潛在的TRT10問題