CrossStagePartialNetworks
CrossStagePartialNetworks copied to clipboard
Did you compare AP and FPS (rather than BFLOPS) of models ?
@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 Yolov3-SPP model
With the same: network resolution, mini_batch=batch/subdivisions, data augmentation, the same dataset - to compare apples with apples.
I found: https://arxiv.org/abs/1911.11929v1
-
CSPResNeXt50-PANet-SPP-GIoU - 35 FPS (+5 FPS) - 60.6 [email protected] - 38.4 [email protected] (+2.2)
-
Yolov3-SPP-(GIoU ???) - 30 FPS - 60.6 [email protected] - 36.2 [email protected]
But did you try backbones CSPDarkNet-53-SPP
and CSPDarkNet-53-Elastic
for Yolov3-spp / PAN?
@AlexeyAB Hello,
Yes, we do comparison of AP, fps, BFLOPs, #parameters.
For big models, due to I have only few GPUs. Training one model need about one and half month. So currently we only have results of CSPResNeXt50-PANet-SPP and CSPResNeXt50-PANet-SPP-GIoU. If you would like to test the speed of other models, I could upload the cfg files.
- CSPResNeXt50-PANet-SPP-GIoU - 35 FPS (+5 FPS) - 60.6 [email protected] - 38.4 [email protected] (+2.2)
This result is for CSPResNeXt50-PANet-SPP, not CSPResNeXt50-PANet-SPP-GIoU.
We focus on AP50, so in our paper, we do not use GIoU.
@WongKinYiu Thanks!
Will you release cfg/weights files for these models?
@AlexeyAB Hmm...
Due to the non-disclosure agreement, I can not release the backbones of lightweight models currently. If you are interested in the EFM(SAM) or PRN, I can share you the head cfg of these models. Well...next month I will try to discuss with the company whether I can release some models or not.
Hi @WongKinYiu
Now it ’s "Next Month".
LOL
Waiting for you share.
@Code-Fight Tomorrow i ll discuss with them.
@WongKinYiu Great Looking forword your good news.
falid :sob: :sob: :sob:
oh....too sad, but thanks for your best
@WongKinYiu Hi
I would like to test csresnet50-elastic-panet-spp.cfg, csresnext50-yolo-spp.cfg, csresnext50-panet-spp.cfg, csresnext50-panet-spp-giou.cfg on gtx1080ti
What should i change in config files for classes = 2 and width=640 height=384
Is it enough to:
- change line classes=80 to 2 in each of 3 [yolo]-layers
- change [filters=255] to filters=(2+ 5)x3 in the 3 [convolutional] before each [yolo] layer as in @AlexeyAB documentation?
Is it possible to use darknet53.conv.74 as initial weight? Or train from scratch?
Thank you.
@dreambit hello,
plz use the pretrained weights from https://github.com/WongKinYiu/CrossStagePartialNetworks#big-models
and follow the https://github.com/AlexeyAB/darknet#how-to-train-tiny-yolo-to-detect-your-custom-objects to get initial weights like csresnext50.conv.80 and so on.
@WongKinYiu Thanks, what about changes in config files with different classes and network size? are there any changes that have to be made except those mentioned in @AlexeyAB docs?
@dreambit
change line classes=80 to 2 in each of 3 [yolo]-layers change [filters=255] to filters=(2+ 5)x3 in the 3 [convolutional] before each [yolo] layer as in @AlexeyAB documentation?
it is enough.
@WongKinYiu Hello
I have almost completed training csresnext50-panet-spp-giou.cfg. Could u provide (if you have one) elastic version of csresnext50-panet-spp[-giou], so i can test it.
Thank you.
@dreambit
https://github.com/WongKinYiu/CrossStagePartialNetworks/blob/master/in%20progress/csresnext50-elastic-panet-spp.cfg here u r.
@WongKinYiu, appreciate it 👍
@WongKinYiu I've changed network size to 640x385, and classes = 2 filters = 21(in each conv. layer before yolo), random = 0
Bug i have 0 mAP.
What is wrong?
Thanks.
@dreambit
Use pre-trained weights.
Set 608x384
https://github.com/AlexeyAB/darknet#how-to-improve-object-detection
increase network resolution in your .cfg-file (height=608, width=608 or any value multiple of 32) - it will increase precision
@AlexeyAB
It was a typo, size is 640x384
@WongKinYiu @AlexeyAB I used wrong initial weights, now it is ok.
@dreambit great!
I have changed network size to 608x608, classes = 40, and filters = 135 (in each conv. layer before yolo), random = 1. I have used csresnext50-panet-spp.cfg and csresnext50c.conv.80 to train my own data set. However, current avg loss = -nan and 0 mAP. What is the problem?
@cmtsai Hello,
csresnext50-panet-spp.cfg should use csresnext50.conv.80 as pre-trained model, not csresnext50c.conv.80.
@WongKinYiu Hello, 3Q very much for your response! How to obtain csresnext50.conv.80?
@WongKinYiu Hi, I got it! 3Q very much!
@WongKinYiu Hi,
Did you try to use Maxout for CSP?
I.e. after route use maxpool_depth:
[route]
layers = 36, 21
[maxpool]
maxpool_depth=1
out_channels=256
stride=1
size=1
@AlexeyAB
Hello, I used maxout in small model. and I applied maxpool_depth before route.
@WongKinYiu Hi,
Why did you add CenterNet resnet-102
instead of CenterNet dla-34
to your comparison table?
@AlexeyAB
Hello, we test CenterNet dla-34
on 1080ti, but it can not reach > 30 fps.
In my test, CenterNet resnet-102
run faster than CenterNet dla-34
almost twice times.
So I only compare with CenterNet resnet-102
.
There are also many issues of inference speed of dla on CenterNet's github. I have not found solution to solve the inference time problem. If you face the problem and solve it, please tell me how to deal with it.