-
Hi everyone,
I wonder if someone can discuss how _fix_padding function work?
Thank you
Cli98 updated
5 years ago
-
First, thanks for the great repo with valuable commented code + support.
I'd like to train a network that matches the aspect ratio of a 1080p resolution. Let's say 1056x608 resolution is close to 108…
-
I build a model and yolov3 is part of it. The picture of losses is below:
As you can s…
-
Hi , i have some question, Alphapose result on coco is good, your group said pytorch-version can achieves 71mAp on COCO dataset. Is this result producted by the "yolov3-spp.weights(from darknet pretra…
-
**Describe the bug**
I used 1024*288 images as a training image, using four 1080ti gpus. I tried to enable both rectangular_training and multi-scale_learning but tensor size mismatch occurred on rou…
-
Hi,
I know this ist exactly ythe right place to post this but maybe someone has some ideas here on how I can solve this issue.
Im trying to predict fairly small object in a small image. I have in…
-
Thanks for your project. I have tested it successfully, but I have something wrong during the training. The information is as follows. Can you give some suggestions?
python train.py
Namespace(accumu…
-
Hi,
Thanks for the awesome work! I've been training using default setting and now is in epoch 241 with the result below (Fig. 1). I have some inquires below.
1. Is the result you report [here](https…
-
I changed my training data to voc format(xml)
and trying to train ppyolo
here are my configuration
TrainReader:
inputs_def:
fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
num_…
-
Hi,
I am trying to use the default yolov3.weights and yolov3.cfg. I came across this strange observation of different bflops and hence different fps while running object detection using `darknet_vide…