LinnaWang76

Results 7 comments of LinnaWang76

make[2]: *** [CMakeFiles/warpctc.dir/build.make:72：CMakeFiles/warpctc.dir/src/warpctc_generated_reduce.cu.o] 错误 1

一样的问题，请问你解决了么

Problem converting ONNX model to TensorRT 7.2.1(CTPN.onnx) (Dynamic ReverseSequence support)

Run ``` ./trtexec --onnx=/path/onnx/file --verbose ``` ``` [12/24/2020-09:29:01] [V] [TRT] /app/onnx-tensorrt/ModelImporter.cpp:129: blstm/transpose_2 [Transpose] inputs: [lambda_1/Reshape:0 -> (32, 32, 512)], [12/24/2020-09:29:01] [V] [TRT] /app/onnx-tensorrt/ImporterContext.hpp:154: Registering layer: blstm/transpose_2 for ONNX node: blstm/transpose_2...

inference时间运行时间差异很大

@zhouzhubin 你这个应该是BN的问题。

evaluation result is different from the paper

你好！你是怎么做的reproduce!我用onet 得到的bbox和score ，参数也跟你一样，可是结果比你的差很多……

where is the pretrain model？ Thx

@felixBrave Thx for your reply!

where is the pretrain model？ Thx

@felixBrave maybe you forget to upload char_std_5990.txt!

Reproduce WIDER score

Hello Could you solve it?i have the same problems! But I got worse results. The same parameters: And have: 0.517 0.329 0.218 I have no idea to reproduce the WIDER...