Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

batch_size>1时在3588上崩溃 #108

Open
ZYX-MLer opened this issue Oct 18, 2023 · 1 comment
Open

batch_size>1时在3588上崩溃 #108

ZYX-MLer opened this issue Oct 18, 2023 · 1 comment

Comments

@ZYX-MLer
Copy link

我在docker上连接开发板调用rknn-toolkit2,可以正常运行batch=2的模型,但是在c++环境中运行到
int ret = rknn_run(ctx, NULL);直接崩溃,没有显示log信息,请问应该如何排查?谢谢。同样的模型batch=1的时候在c++中也是正常的,

我在docker中连接开发板调试显示:
RKNN VERSION:
D RKNNAPI: API: 1.5.2 (8babfea build@2023-08-25T02:31:12)
D RKNNAPI: DRV: rknn_server: 1.5.2 (8babfea build@2023-08-25T10:30:12)
D RKNNAPI: DRV: rknnrt: 1.5.2 (c6b7b351a@2023-08-23T15:27:35)

在c++环境调用
rknn_sdk_version sdk_ver;
ret = rknn_query(ctx, RKNN_QUERY_SDK_VERSION, &sdk_ver, sizeof(sdk_ver));
显示:
api_version = {char [256]}1.5.2
drv_version = {char [256]}0.8.2

ret = rknn_query(ctx, RKNN_QUERY_MEM_SIZE, &mem_size, sizeof(mem_size));
mem_size = {rknn_mem_size}
total_weight_size = {uint32_t} 2816192
total_internal_size = {uint32_t} 6627072
total_dma_allocated_size = {uint64_t} 6201344
total_sram_size = {uint32_t} 0
free_sram_size = {uint32_t} 0
reserved = {uint32_t [10]}

@S0soo
Copy link

S0soo commented Jun 11, 2024

您好,请问batch=2时,输入的buf是如何设置的,我尝试使用std::vectorcv::Mat来接收两个image,并把vector.data赋给input.buf[],能执行但是输出有问题,也尝试将两个Mat.data memcpy 到一个uchar* buf内,同样能执行但是输出有问题,请问您是如何设置input buf的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants