Alexey

I get the ~same FPS by using -numncs 1 and -numncs 2

5

I should get **2x** more FPS by using -numncs, isn't it? **[Required]** Custom device Atom CPU + 2 x MyriadX (VPU) via mini-PCI-express **[Required]** Your device's CPU architecture **x86_64** Intel...

Try to train fast (grouped-conv) versions of csdarknet53 and csdarknet19

109

@WongKinYiu Hi, Since CSPDarkNet53 is better than CSPResNeXt50 for Detector, try to train these 4 models: | Model | GPU | 256x256 | 512x512 | 608x608 | | :-- |...

Did you compare AP and FPS (rather than BFLOPS) of models ?

39

@WongKinYiu Hi, Did you compare `AP` (MS COCO) and `1080ti fps` (rather than BFLOPS) of models ? * CSPResNeXt50-PANet-SPP-GIoU https://github.com/WongKinYiu/CrossStagePartialNetworks#gpu-real-time-models * CSPDarkNet-53-SPP-GIoU-Yolov3 that is based on `CSPDarkNet-53` https://github.com/WongKinYiu/CrossStagePartialNetworks#big-models * default...

Do you know why just one small change (1 line) greatly improves accuracy +0.7 on Pytorch-yolo?

3

@WongKinYiu Hi, Do you know why just one small change (**1 line**) greatly improves accuracy `+ 0.7` on Pytorch-yolo? https://github.com/WongKinYiu/CrossStagePartialNetworks/blob/pytorch/README.md | Model | Size | NMS | 1080ti *fps* |...

Why does onnx-tensorflow add Transpose layers for each Conv2D layer?

7

**Describe the bug** 1. Why does `onnx-tensorflow` add **Transpose** layers for each Conv2D layer? 2. Why does `onnx-tensorflow` use multiple Conv2D layers instead of one GroupedConv2D layer? It increases inference...

Why do you use Convolutional layers without Batch-normalization in RFBblock?

1

@ruinmessi Hi, Why do you use Convolutional layers without Batch-normalization in RFBblock? https://github.com/ruinmessi/ASFF/blob/55b6637b21d69509ae73100f9db19dc98acb419d/models/network_blocks.py#L138-L159

Official YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

5

### Official YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors * **paper:** https://arxiv.org/abs/2207.02696 * **source code - Pytorch (use to reproduce results):** https://github.com/WongKinYiu/yolov7 ---- Darknet cfg/weights file -...

Darknet Yolo v2 is added to the OpenCV

16

Now Darknet Yolo v2 is added to the OpenCV: https://github.com/opencv/opencv/pull/9705 You can use it from master-branch or since OpenCV 3.4.0 will be released. There is example how to use Yolo...

YOLOR - You Only Learn One Representation: Unified Network for Multiple Tasks

2

YOLOR - You Only Learn One Representation: Unified Network for Multiple Tasks: YOLOR is better than YOLOv5 (u5r5), PP-YOLOv2, CenterNet2, EfficientDet and many other * **paper**: https://arxiv.org/abs/2105.04206 * **Pytorch** code:...

@Ma-Dan Hi, Did you test accuracy of converted YOLOv4-model on MSCOCO? Is it the same as in the Darknet - 43.5% AP (65.7% AP50) for YOLOv4-608x608?