-
i trained some feed forward neural networks using the mnist dataset with the sigmoid activation and converted them into the smt2 format.
now i want to test specific records of the mnist dataset to se…
Krayn updated
2 years ago
-
### Describe the feature and motivation
I am trying to load a yolov3 model in ONNX format. When calling cv::dnn::readNetFromONNX() i get error:
```
[ERROR:0@0.322] global onnx_importer.cpp:1036 h…
-
I have two questions about dnn descriptor with DBoW3:
1. dnn descriptor seems too small for DBoW3: for example, superpoint, it is float 256 descriptor and I normalize to [0,1], it seems DBoW3 don'…
-
`opencv_dnn.blobFromImages` method supports multiple pictures inference at the same time. Is it necessary to put at least two pictures?
I found that when I put in only one picture, I didn't get the r…
-
GPUDirect vs CUDA-Aware MPI
- http://timdettmers.com/2014/09/21/how-to-build-and-use-a-multi-gpu-system-for-deep-learning/
- http://timdettmers.com/2014/11/09/model-parallelism-deep-learning/
- …
-
How to solve this?:
```
OpenCV(3.4.1) Error: Parsing error (Unknown layer type: shortcut) in ReadDarknetFromCfgFile, file /io/opencv/modules/dnn/src/darknet/darknet_io.cpp, line 503
Traceback (mo…
-
I have many dnn installations that need upgrading to 9+. Can we discuss costs for making this module work in version 9?
-
Dear OPSI Team
I just wanted to ask if there is any version of your great UManage Tool available that works on current DNN9 Version too.
Unfortunately the DNN8 Version does not show any users in m…
-
How about making an original character of ruby dnn? A logo has a great power to attract people. I like drawing pictures. When I saw your twitter, I felt that you also like drawing pictures.
(After …
-
when i use cv2.dnn.readNet() to read the onnx model, i have a question
(expected: 'shapes.depth() == CV_32S') where 'shapes.depth()' is 5(CV_32FC1)
must be equal to 'CV_32S' is 4(CV_32SC1) in void_…