Fix broken links in docs (#19734)
This commit is contained in:
parent
a40957ec00
commit
e19c64fc4a
@ -230,7 +230,7 @@ The Ultralytics command-line interface (CLI) allows for simple single-line comma
|
||||
|
||||
=== "Inference with Streamlit"
|
||||
|
||||
Perform object detection, instance segmentation, or pose estimation in a web browser using [Streamlit](https://www.ultralytics.com/reference/solutions/streamlit_inference):
|
||||
Perform object detection, instance segmentation, or pose estimation in a web browser using [Streamlit](https://docs.ultralytics.com/reference/solutions/streamlit_inference):
|
||||
```bash
|
||||
yolo solutions inference
|
||||
|
||||
|
||||
@ -154,7 +154,7 @@ Adjust these settings to meet dataset and task requirements. Experimenting with
|
||||
|
||||
Logging, checkpoints, plotting, and file management are important when training a YOLO model:
|
||||
|
||||
- **Logging**: Track the model's progress and diagnose issues using libraries like [TensorBoard](https://www.ultralytics.com/integrations/tensorboard) or by writing to a file.
|
||||
- **Logging**: Track the model's progress and diagnose issues using libraries like [TensorBoard](https://docs.ultralytics.com/integrations/tensorboard) or by writing to a file.
|
||||
- **Checkpoints**: Save the model at regular intervals to resume training or experiment with different configurations.
|
||||
- **Plotting**: Visualize performance and training progress using libraries like matplotlib or TensorBoard.
|
||||
- **File management**: Organize files generated during training, such as checkpoints, log files, and plots, for easy access and analysis.
|
||||
|
||||
@ -58,7 +58,7 @@ trainer = CustomTrainer(overrides={...})
|
||||
trainer.train()
|
||||
```
|
||||
|
||||
Further customize the trainer by modifying the [loss function](https://www.ultralytics.com/glossary/loss-function) or adding a [callback](https://www.ultralytics.com/glossary/callback) to upload the model to Google Drive every 10 [epochs](https://www.ultralytics.com/glossary/epoch). Here's an example:
|
||||
Further customize the trainer by modifying the [loss function](https://www.ultralytics.com/glossary/loss-function) or adding a [callback](callbacks.md) to upload the model to Google Drive every 10 [epochs](https://www.ultralytics.com/glossary/epoch). Here's an example:
|
||||
|
||||
```python
|
||||
from ultralytics.models.yolo.detect import DetectionTrainer
|
||||
|
||||
@ -195,7 +195,7 @@ For example, users can load a model, train it, evaluate its performance on a val
|
||||
|
||||
=== "Export to ONNX"
|
||||
|
||||
Export an official YOLO model to [ONNX](https://www.ultralytics.com/glossary/onnx) with dynamic batch-size and image-size.
|
||||
Export an official YOLO model to [ONNX](https://www.ultralytics.com/glossary/onnx-open-neural-network-exchange) with dynamic batch-size and image-size.
|
||||
```python
|
||||
from ultralytics import YOLO
|
||||
|
||||
|
||||
@ -84,7 +84,7 @@ convert_segment_masks_to_yolo_seg(masks_dir="path/to/masks_dir", output_dir="pat
|
||||
|
||||
### Convert COCO into YOLO Format
|
||||
|
||||
Use this to convert [COCO](https://www.ultralytics.com/datasets/detect/coco) JSON annotations into the YOLO format. For object detection (bounding box) datasets, set both `use_segments` and `use_keypoints` to `False`.
|
||||
Use this to convert [COCO](https://docs.ultralytics.com/datasets/detect/coco) JSON annotations into the YOLO format. For object detection (bounding box) datasets, set both `use_segments` and `use_keypoints` to `False`.
|
||||
|
||||
```python
|
||||
from ultralytics.data.converter import convert_coco
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user