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
+1-16Lines changed: 1 addition & 16 deletions
Original file line number
Diff line number
Diff line change
@@ -50,6 +50,7 @@ We validated the performance of RF-DETR on both Microsoft COCO and the RF100-VL
50
50
## News
51
51
52
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.
53
54
54
55
## Installation
55
56
@@ -390,10 +391,6 @@ Different GPUs have different VRAM capacities, so adjust batch_size and grad_acc
390
391
391
392
### Resume training
392
393
393
-
> [!IMPORTANT]
394
-
> Resume support isn’t officially released yet.
395
-
> Install from source to access it: `pip install git+https://github.com/roboflow/rf-detr.git`.
396
-
397
394
You can resume training from a previously saved checkpoint by passing the path to the `checkpoint.pth` file using the `resume` argument. This is useful when training is interrupted or you want to continue fine-tuning an already partially trained model. The training loop will automatically load the weights and optimizer state from the provided checkpoint file.
> Install from source to access it: `pip install git+https://github.com/roboflow/rf-detr.git`.
412
-
413
406
Early stopping monitors validation mAP and halts training if improvements remain below a threshold for a set number of epochs. This can reduce wasted computation once the model converges. Additional parameters—such as `early_stopping_patience`, `early_stopping_min_delta`, and `early_stopping_use_ema`—let you fine-tune the stopping behavior.
414
407
415
408
```python
@@ -436,10 +429,6 @@ During training, two model checkpoints (the regular weights and an EMA-based set
436
429
437
430
### Logging with TensorBoard
438
431
439
-
> [!IMPORTANT]
440
-
> TensorBoard support isn’t officially released yet.
441
-
> Install from source to access it: `pip install git+https://github.com/roboflow/rf-detr.git`.
442
-
443
432
[TensorBoard](https://www.tensorflow.org/tensorboard) is a powerful toolkit that helps you visualize and track training metrics. With TensorBoard set up, you can train your model and keep an eye on the logs to monitor performance, compare experiments, and optimize model training. To enable logging, simply pass `tensorboard=True` when training the model.
444
433
445
434
<details>
@@ -490,10 +479,6 @@ During training, two model checkpoints (the regular weights and an EMA-based set
490
479
491
480
### Logging with Weights and Biases
492
481
493
-
> [!IMPORTANT]
494
-
> Weights and Biases support isn’t officially released yet.
495
-
> Install from source to access it: `pip install git+https://github.com/roboflow/rf-detr.git`.
496
-
497
482
[Weights and Biases (W&B)](https://www.wandb.ai) is a powerful cloud-based platform that helps you visualize and track training metrics. With W&B set up, you can monitor performance, compare experiments, and optimize model training using its rich feature set. To enable logging, simply pass `wandb=True` when training the model.
0 commit comments