关于模型转换的问题

[PIPItian]

您好，我在自己的电脑运行./convertModel ./solov2_r50_fpn_8gpu_3x.onnx -g ./seg_coco_permute.bin时出现以下错误

-->Generate model start

Input filename: solov2_r50_fpn_8gpu_3x.onnx
ONNX IR version: 0.0.6
Opset version: 11
Producer name: pytorch
Producer version: 1.7
Domain:
Model version: 0
Doc string:

ERROR: ModelImporter.cpp:92 In function parseGraph:
[8] Assertion failed: convertOnnxWeights(initializer, &weights, ctx)
Assertion failed: convertOnnxWeights(initializer, &weights, ctx)
-->Check your CUDA version
-->Load o-n-n-x stream done
[10/18/2022-09:19:11] [E] [TRT] Network must have at least one output
[10/18/2022-09:19:11] [E] [TRT] Network validation failed.
-->Check your CUDA version
Segmentation fault (core dumped)

使用的时CUDA10.0 tensorRT 7.0，请问博主使用的环境是什么呢？如果方便的话可以提供一下转换出来的.bin 文件吗

[Broad-sky]

您好，我在自己的电脑运行./convertModel ./solov2_r50_fpn_8gpu_3x.onnx -g ./seg_coco_permute.bin时出现以下错误

-->Generate model start

Input filename: solov2_r50_fpn_8gpu_3x.onnx ONNX IR version: 0.0.6 Opset version: 11 Producer name: pytorch Producer version: 1.7 Domain: Model version: 0 Doc string:

ERROR: ModelImporter.cpp:92 In function parseGraph: [8] Assertion failed: convertOnnxWeights(initializer, &weights, ctx) Assertion failed: convertOnnxWeights(initializer, &weights, ctx) -->Check your CUDA version -->Load o-n-n-x stream done [10/18/2022-09:19:11] [E] [TRT] Network must have at least one output [10/18/2022-09:19:11] [E] [TRT] Network validation failed. -->Check your CUDA version Segmentation fault (core dumped)

使用的时CUDA10.0 tensorRT 7.0，请问博主使用的环境是什么呢？如果方便的话可以提供一下转换出来的.bin 文件吗

CUDA10.0 tensorRT 7.0低了，建议10.2+ 7.3+