ACR-Instance-Segmentation
Collection
19 items โข Updated โข 1
ACR ํ๊ฒฝ์ ๊ฐ์ฒด ๊ฒ์ถ ๋ฐ instance segmentation์ ์ํ RF-DETR Seg2XLarge ๋ฐฐํฌ ๋ชจ๋ธ์ ๋๋ค.
| ํ์ผ | ์ค๋ช |
|---|---|
cmes_RF_960_v1.0.0.pth |
RF-DETR Seg2XLarge PyTorch best weight |
config.yaml |
๋ชจ๋ธ ๊ตฌ์กฐ, ์ถ๋ก ์ค์ , ํด๋์ค ์์ ๋ฐ ๊ฒ์ฆ ๊ฒฐ๊ณผ |
960 x 9600.50300111.9.0python -m pip install rfdetr==1.9.0 torch torchvision pillow numpy pyyaml
from huggingface_hub import hf_hub_download
weight_path = hf_hub_download(
repo_id="cmes-deepvision/ACR-instance-segmentation-RF-v1.0.0",
filename="cmes_RF_960_v1.0.0.pth",
)
import torch
from PIL import Image
from rfdetr import RFDETRSeg2XLarge
model = RFDETRSeg2XLarge.from_checkpoint(
weight_path,
trust_checkpoint=True,
resolution=960,
device="cuda:0",
)
model.inference(compile=False, batch_size=1, dtype=torch.float16)
image = Image.open("image.jpg").convert("RGB")
detections = model.predict(
image,
threshold=0.50,
shape=(960, 960),
patch_size=12,
include_source_image=False,
)
์ด ํ์ผ์ PyTorch pickle ๊ธฐ๋ฐ ํ์์ด๋ฏ๋ก ๊ณต์ ์ ์ฅ์์์ ๋ฐ์ ํ์ผ์๋ง
trust_checkpoint=True๋ฅผ ์ฌ์ฉํ์ญ์์ค. ํด๋์ค ID๋ ์๋ ์์๋ฅผ ๋ฐ๋ฆ
๋๋ค.
0 dropping item
1 dumping item
2 item in pb bag
3 item in tote
4 item on buffer
5 item on floor
6 item on plate
7 item out of buffer
8 item out of tote
9 picked item
10 tote
Test_v2.2.1 ์ ์ฒด 6,475์ฅ, 50 tasks, confidence 0.50, IoU 0.50 ๊ธฐ์ค์
๋๋ค.
| Precision | Recall | F1 | bbox mAP50 | segm mAP50 |
|---|---|---|---|---|
| 0.9054 | 0.8509 | 0.8657 | 0.8411 | 0.8454 |
์ด์ threshold๋ฅผ ๋ณ๊ฒฝํ๋ฉด Precision๊ณผ Recall๋ ๋ฌ๋ผ์ง๋ฏ๋ก ๊ธฐ๋ณธ๊ฐ 0.50์์ ๋จผ์ ๊ฒ์ฆํ์ญ์์ค.