Ghustwb
Ghustwb
> @Ghustwb > In TensorRT4 the API allows you to specify the order/layout of the input, not in TensorRT3 though > You can find description of the API [here](https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/structnvinfer1_1_1plugin_1_1_detection_output_parameters.html) Thanks...
> @Ghustwb Maybe try working with another repo like [this one](https://github.com/Teoge/tensorrt-ssd-easy) > And check the plugin layer name carefully, when I worked on mobilenetSSD I was sure I had them...
| | 卢晨光 | | 邮箱：[email protected] | 签名由 网易邮箱大师 定制 On 12/06/2018 01:41, yehao wrote: In tensorRT 4.0 doc: It supports softmax on C, H, W dimension — You are...
Great!
> Hi @Ghustwb , Thanks for your works, i've been looking into this repo for quite a while. Thanks . Now I'm here with another simple doubt. Is it possible...
I met the same problems.when read 640*480 video ,is normal ,but read 1080P ,the error is "the feature2MatrixInit failed!!" how can I fix it? Thaks
@JingliangGao My mobilenet-ssd shape output is INPUT Tensor Shape is: C: 3 H: 300 W: 300 mbox_conf_softmax Tensor Shape is: C: 1917 H:21 W: 1 mbox_loc Tensor Shape is: C:...
@myih Thanks for your reply The part of image loader was different with chuanqi305,and I changed it. But there are still problems here，detection_out output 0 15 0.98 0.249136 0.45 0.251...
I also noticed the phenomenon. I do not konw why
@zbw4034 I tried tensorRT on pelee(tensorRT3) About 115fps on gtx1080(MobileNet-SSD about 150fps on gtx 1080)