ice6

I hope this can be helpful for the web ui https://gist.github.com/ice6/b1977b11e68686974d737ea082ec278b

+1

https://github.com/krakjoe/wkhtmltox/pull/10

+1. it needs more resources to train the model.

it works now! can this issue be closed?

@tjbck I am on `dev` branch, the bug still exists. although the fix is not perfect, but the error was fixed and pdf can be exported. so you guys can...

> 使用model.export转换的模型，请使用如下参数配置： > > ``` > "name": "yolov8n-640", > "input_size": 640, > "param": "yolov8n.param", > "bin": "yolov8n.bin", > "box_thr": 0.25, > "iou_thr": 0.35, > "ver": 8, > "input_name": "in0", >...

yolov8的格式转换存在一些问题，用它的命令行可以正确转换，用代码方式就不行了。（贴在这里方便后面看到这个帖子的人） `yolo export format=ncnn model=runs/detect/train/weights/best.pt imgsz=640` Ultralytics YOLOv8.2.98 🚀 Python-3.10.14 torch-2.4.1 CPU (13th Gen Intel Core(TM) i9-13900HX) YOLOv8x summary (fused): 268 layers, 68,145,717 parameters, 0 gradients, 257.5 GFLOPs PyTorch: starting...

可以加载，我用的最新的android studio，并确保下载的aar文件没问题，可以sha256sum看下。

vote for `Client Size Resizing`.