-
Learning Spatial Fusion for Single-Shot Object Detection
* paper [https://arxiv.org/pdf/1911.09516.pdf](https://arxiv.org/pdf/1911.09516.pdf)
* code [https://github.com/ruinmessi/ASFF](https://gith…
-
Hello
How are you?
Thanks for contributing this project.
Could u support to use Yolov5 model(*.pt) in this project?
Thanks
-
[13-CURRENT based Live ISO](https://github.com/helloSystem/ISO/releases/tag/continuous-13.0-CURRENT) does not boot. Getting
```
lock order reversal:
isofs -> bufwait established at:
(...)
md.c:…
-
- Error
```2021-04-28 11:17:02,946-WARNING: fail to map op [Gt2YoloTarget_dbee5d] with error: index 834 is out of bounds for axis 1 with size 56 and stack:
Traceback (most recent call last):
Fi…
-
**Describe the bug**
Building ffmpeg-full on Darwin fails in the configure step, with the following error message:
```
configure flags: --disable-static --prefix=/nix/store/dhrqbjnamwz1xw3p9h463q…
bcc32 updated
3 years ago
-
Have you tried the Gaussian object detection method?
* cfg files: https://github.com/jwchoi384/Gaussian_YOLOv3/tree/master/cfg
* BDD100k weights file: https://drive.google.com/open?id=1Eutnens-3z6…
-
when i run darknet, it was done. i could get result image by using pre-trained model.
but when i train my own data, there was one error even i already checked my cfg and data set
CUDA Error Prev: …
-
代码中spp是这样的：
```
def Spp_Conv2D_BN_Leaky(x, num_filters):
y1 = MaxPooling2D(pool_size=(5,5), strides=(1,1), padding='same')(x)
y2 = MaxPooling2D(pool_size=(9,9), strides=(1,1), padding='sam…
-
Hi, i have a decrease in performance with CUDNN_HALF=1
Last git code (Date: Tue Jan 14 00:21:39 2020 +0300)
Xavier
GPU=1
CUDNN=1
CUDNN_HALF=1
OPENCV=0
AVX=0
OPENMP=1
LIBSO=0
ZED_CAM…
-