You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+9-8Lines changed: 9 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,6 +18,15 @@ RF-DETR is small enough to run on the edge using [Inference](https://github.com/
18
18
19
19
[Read the documentation to get started training.](https://rfdetr.roboflow.com)
20
20
21
+
## News
22
+
23
+
-`2025/07/23`: We release three new checkpoints for RF-DETR: Nano, Small, and Medium.
24
+
- RF-DETR Base is now deprecated. We recommend using RF-DETR Medium which offers subtantially better accuracy at comparable latency.
25
+
-`2025/03/20`: We release RF-DETR real-time object detection model. **Code and checkpoint for RF-DETR-large and RF-DETR-base are available.**
26
+
-`2025/04/03`: We release early stopping, gradient checkpointing, metrics saving, training resume, TensorBoard and W&B logging support.
27
+
-`2025/05/16`: We release an 'optimize_for_inference' method which speeds up native PyTorch by up to 2x, depending on platform.
28
+
-`2025/07/23`: We release new SOTA model sizes: RF-DETR-Nano, RF-DETR-Small, RF-DETR-Medium.
29
+
21
30
## Results
22
31
23
32
RF-DETR achieves state-of-the-art performance on both the Microsoft COCO and the RF100-VL benchmarks.
@@ -46,14 +55,6 @@ The table below shows the performance of RF-DETR medium, compared to comparable
46
55
47
56
_We are actively working on a new RF-DETR Large model that will substantially outperform the current RF-DETR Large available in this repository. This is why RF-DETR Large is not yet reported on our pareto graph. Check back in the next few weeks for our RF-DETR Large launch._
48
57
49
-
## News
50
-
51
-
-`2025/07/23`: We release three new checkpoints for RF-DETR: Nano, Small, and Medium.
52
-
-`2025/03/20`: We release RF-DETR real-time object detection model. **Code and checkpoint for RF-DETR-large and RF-DETR-base are available.**
53
-
-`2025/04/03`: We release early stopping, gradient checkpointing, metrics saving, training resume, TensorBoard and W&B logging support.
54
-
-`2025/05/16`: We release an 'optimize_for_inference' method which speeds up native PyTorch by up to 2x, depending on platform.
55
-
-`2025/07/23`: We release new SOTA model sizes: RF-DETR-Nano, RF-DETR-Small, RF-DETR-Medium.
56
-
57
58
## Installation
58
59
59
60
Pip install the `rfdetr` package in a [**Python>=3.9**](https://www.python.org/) environment.
0 commit comments