xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-24 06:07:03 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Benchmark with custom data.yaml (#3858)

Browse Source 
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Maia Numerosky 2023-07-20 20:44:46 -03:00 committed by GitHub
parent 01dcd54b19
commit aa1cab74f8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 19 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
docs/modes/benchmark.md
View File

@ -30,27 +30,28 @@ full list of export arguments.
from ultralytics.utils.benchmarks import benchmark from ultralytics.utils.benchmarks import benchmark
# Benchmark on GPU # Benchmark on GPU
benchmark(model='yolov8n.pt', imgsz=640, half=False, device=0) benchmark(model='yolov8n.pt', data='coco8.yaml', imgsz=640, half=False, device=0)
``` ```
=== "CLI" === "CLI"
```bash ```bash
yolo benchmark model=yolov8n.pt imgsz=640 half=False device=0 yolo benchmark model=yolov8n.pt data='coco8.yaml' imgsz=640 half=False device=0
``` ```
## Arguments ## Arguments
Arguments such as `model`, `imgsz`, `half`, `device`, and `hard_fail` provide users with the flexibility to fine-tune Arguments such as `model`, `data`, `imgsz`, `half`, `device`, and `hard_fail` provide users with the flexibility to fine-tune
the benchmarks to their specific needs and compare the performance of different export formats with ease. the benchmarks to their specific needs and compare the performance of different export formats with ease.
| Key | Value | Description | | Key | Value | Description |
|-------------|---------|----------------------------------------------------------------------| |-------------|---------|----------------------------------------------------------------------------|
| `model` | `None` | path to model file, i.e. yolov8n.pt, yolov8n.yaml | | `model` | `None` | path to model file, i.e. yolov8n.pt, yolov8n.yaml |
| `imgsz` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) | | `data` | `None` | path to yaml referencing the benchmarking dataset (under `val` label) |
| `half` | `False` | FP16 quantization | | `imgsz` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) |
| `int8` | `False` | INT8 quantization | | `half` | `False` | FP16 quantization |
| `device` | `None` | device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu | | `int8` | `False` | INT8 quantization |
| `hard_fail` | `False` | do not continue on error (bool), or val floor threshold (float) | | `device` | `None` | device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu |
| `hard_fail` | `False` | do not continue on error (bool), or val floor threshold (float) |
## Export Formats ## Export Formats

2
docs/usage/python.md
View File

@ -243,7 +243,7 @@ their specific use case based on their requirements for speed and accuracy.
from ultralytics.utils.benchmarks import benchmark from ultralytics.utils.benchmarks import benchmark
# Benchmark # Benchmark
benchmark(model='yolov8n.pt', imgsz=640, half=False, device=0) benchmark(model='yolov8n.pt', data='coco8.yaml', imgsz=640, half=False, device=0)
``` ```
[Benchmark Examples](../modes/benchmark.md){ .md-button .md-button--primary} [Benchmark Examples](../modes/benchmark.md){ .md-button .md-button--primary}

6
ultralytics/utils/benchmarks.py
View File

@ -5,7 +5,7 @@ Benchmark a YOLO model formats for speed and accuracy
Usage: Usage:
from ultralytics.utils.benchmarks import ProfileModels, benchmark from ultralytics.utils.benchmarks import ProfileModels, benchmark
ProfileModels(['yolov8n.yaml', 'yolov8s.yaml']).profile() ProfileModels(['yolov8n.yaml', 'yolov8s.yaml']).profile()
run_benchmarks(model='yolov8n.pt', imgsz=160) benchmark(model='yolov8n.pt', imgsz=160)
Format | `format=argument` | Model Format | `format=argument` | Model
--- | --- | --- --- | --- | ---
@ -44,6 +44,7 @@ from ultralytics.utils.torch_utils import select_device
def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt', def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
data=None,
imgsz=160, imgsz=160,
half=False, half=False,
int8=False, int8=False,
@ -55,6 +56,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
Args: Args:
model (str | Path | optional): Path to the model file or directory. Default is model (str | Path | optional): Path to the model file or directory. Default is
Path(SETTINGS['weights_dir']) / 'yolov8n.pt'. Path(SETTINGS['weights_dir']) / 'yolov8n.pt'.
data (str, optional): Dataset to evaluate on, inherited from TASK2DATA if not passed. Default is None.
imgsz (int, optional): Image size for the benchmark. Default is 160. imgsz (int, optional): Image size for the benchmark. Default is 160.
half (bool, optional): Use half-precision for the model if True. Default is False. half (bool, optional): Use half-precision for the model if True. Default is False.
int8 (bool, optional): Use int8-precision for the model if True. Default is False. int8 (bool, optional): Use int8-precision for the model if True. Default is False.
@ -106,7 +108,7 @@ def benchmark(model=Path(SETTINGS['weights_dir']) / 'yolov8n.pt',
export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half) export.predict(ROOT / 'assets/bus.jpg', imgsz=imgsz, device=device, half=half)
# Validate # Validate
data = TASK2DATA[model.task] # task to dataset, i.e. coco8.yaml for task=detect data = data or TASK2DATA[model.task] # task to dataset, i.e. coco8.yaml for task=detect
key = TASK2METRIC[model.task] # task to metric, i.e. metrics/mAP50-95(B) for task=detect key = TASK2METRIC[model.task] # task to metric, i.e. metrics/mAP50-95(B) for task=detect
results = export.val(data=data, results = export.val(data=data,
batch=1, batch=1,