Skip to content

Commit 5e2979d

Browse files
authored
Merge pull request #108 from roboflow/1.1.0-release
Final updates before 1.1.0 release
2 parents 00daf5e + be14c25 commit 5e2979d

File tree

2 files changed

+2
-17
lines changed

2 files changed

+2
-17
lines changed

README.md

Lines changed: 1 addition & 16 deletions
Original file line numberDiff line numberDiff line change
@@ -50,6 +50,7 @@ We validated the performance of RF-DETR on both Microsoft COCO and the RF100-VL
5050
## News
5151

5252
- `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.
5354

5455
## Installation
5556

@@ -390,10 +391,6 @@ Different GPUs have different VRAM capacities, so adjust batch_size and grad_acc
390391

391392
### Resume training
392393

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-
397394
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.
398395

399396
```python
@@ -406,10 +403,6 @@ model.train(dataset_dir=<DATASET_PATH>, epochs=10, batch_size=4, grad_accum_step
406403

407404
### Early stopping
408405

409-
> [!IMPORTANT]
410-
> Early stopping isn’t officially released yet.
411-
> Install from source to access it: `pip install git+https://github.com/roboflow/rf-detr.git`.
412-
413406
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.
414407

415408
```python
@@ -436,10 +429,6 @@ During training, two model checkpoints (the regular weights and an EMA-based set
436429

437430
### Logging with TensorBoard
438431

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-
443432
[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.
444433

445434
<details>
@@ -490,10 +479,6 @@ During training, two model checkpoints (the regular weights and an EMA-based set
490479

491480
### Logging with Weights and Biases
492481

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-
497482
[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.
498483

499484
<details>

pyproject.toml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
44

55
[project]
66
name = "rfdetr"
7-
version = "1.1.0rc0"
7+
version = "1.1.0"
88
description = "RF-DETR"
99
readme = "README.md"
1010
authors = [

0 commit comments

Comments
 (0)