-
Notifications
You must be signed in to change notification settings - Fork 84
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
about Forward_DetectionOutputLayer function #26
Comments
Hi, |
@chenzhi1992 I tried the code and able to run it on X86_64 machine, for model trained on VOC dataset and also model trained on custom dataset (classes less than 21). |
Hi @chenzhi1992 have you tried using it with a number of classes different to 21? |
The dimension of mbox_priorbox is wrong, and you can check it again. @paghdv |
I have exactly the same dimension that I have in caffe: (1,2,122656,1) (NCHW) |
@paghdv @chenzhi1992 |
@myih I ended-up just implementing detection_out. Mobilenet-SSD runs but you have to implement the depthwise conv layer yourself to see any speedups otherwise uses the default (loop through groups) method in TensorRT that is very slow. |
@paghdv Thanks for the fast reply. I'm able to use the createSSDDetectionOutputPlugin to run VGG-SSD so maybe it's not the detection-layer's problem? |
@paghdv |
@myih how did you solve it?Could you show me more details? |
Yes, I do get the correct result with grouped convolutions.
On Mon, Aug 13, 2018, 6:16 PM myih ***@***.***> wrote:
@paghdv <https://github.com/paghdv>
I solve the error by updating to TensorRT4 and specify inputOrder = {0, 1,
2}, but the detection output result is incorrect.
Were you able to get correct output when using group convolution and not
your own depthwise convolution?
Thank you!
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#26 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/ADhxI7USbt-1OiC2SJ6YHZi-xWkb5UUtks5uQiT3gaJpZM4UFmEs>
.
--
AG
|
@myih did you implement your own softmax? |
@paghdv I use this implementation Teoge/tensorrt-ssd-easy , it works for vgg-ssd and I checked the cuda code seems legit. |
Damn I totally forgot about Weiliu and chuanqi305 use different image loader... |
what is the meaning of "setting inputOrder = {0, 1, 2} in createSSDDetectionOutputPlugin"? could you describe is in detail? Please |
Thanks for your reply,I tried tensorRT4.0,use "setting inputOrder = {0, 1, 2} in createSSDDetectionOutputPlugin",the Assertion error still exists virtual void nvinfer1::plugin::DetectionOutput::configure(const nvinfer1::Dims*, int, const nvinfer1::Dims*, int, int): Assertion numPriorsnumLocClasses4 == inputDims[param.inputOrder[0]].d[0]' failed |
Thank you for your help, mobileNet-SSD runs successfully. Can you help me? Thanks |
Hi:
first ,thanks for your code samples,but i do not understand how to use "Forward_DetectionOutputLayer"?
i see your comment "I removed the 'detection_out' layer, and calculated the final output through the mbox_loc, mbox_prior and mbox_conf layer output"
but the "mbox_loc " plugin layer is use the "createConcatPlugin" ,how to get this layer's outputs?
i think that it should rewrite interface for DetectionOut like "class DetectionOut : public IPlugin"
and in the enqueue(int batchSize, const void*const inputs, void* outputs) function to get the input as mbox_loc,how do you think about it ?
@chenzhi1992
The text was updated successfully, but these errors were encountered: