HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.2.14 add task + OBB to hub.check_dataset() (#12573)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Burhan 2024-05-12 15:27:44 -04:00 • committed by GitHub
parent cf24349efb
commit fd748e3c7a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 36 additions and 24 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/test_python.py
View file

@ -12,7 +12,7 @@ import yaml
from PIL import Image
from ultralytics import RTDETR, YOLO
from ultralytics.cfg import MODELS, TASK2DATA
from ultralytics.cfg import MODELS, TASKS, TASK2DATA
from ultralytics.data.build import load_inference_source
from ultralytics.utils import (
ASSETS,
@ -98,6 +98,12 @@ def test_predict_img(model_name):
assert len(model(batch, imgsz=32)) == len(batch) # multiple sources in a batch
@pytest.mark.parametrize("model", MODELS)
def test_predict_visualize(model):
"""Test model predict methods with 'visualize=True' arguments."""
YOLO(WEIGHTS_DIR / model)(SOURCE, imgsz=32, visualize=True)
def test_predict_grey_and_4ch():
"""Test YOLO prediction on SOURCE converted to greyscale and 4-channel images."""
im = Image.open(SOURCE)
@ -267,7 +273,7 @@ def test_data_utils():
# from ultralytics.utils.files import WorkingDirectory
# with WorkingDirectory(ROOT.parent / 'tests'):
for task in "detect", "segment", "pose", "classify":
for task in TASKS:
file = Path(TASK2DATA[task]).with_suffix(".zip") # i.e. coco8.zip
download(f"https://github.com/ultralytics/hub/raw/main/example_datasets/{file}", unzip=False, dir=TMP)
stats = HUBDatasetStats(TMP / file, task=task)

2
ultralytics/__init__.py
View file

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.2.13"
__version__ = "8.2.14"
from ultralytics.data.explorer.explorer import Explorer
from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld

5
ultralytics/data/utils.py
View file

@ -441,6 +441,7 @@ class HUBDatasetStats:
stats = HUBDatasetStats('path/to/coco8.zip', task='detect') # detect dataset
stats = HUBDatasetStats('path/to/coco8-seg.zip', task='segment') # segment dataset
stats = HUBDatasetStats('path/to/coco8-pose.zip', task='pose') # pose dataset
stats = HUBDatasetStats('path/to/dota8.zip', task='obb') # OBB dataset
stats = HUBDatasetStats('path/to/imagenet10.zip', task='classify') # classification dataset
stats.get_json(save=True)
@ -497,13 +498,13 @@ class HUBDatasetStats:
"""Update labels to integer class and 4 decimal place floats."""
if self.task == "detect":
coordinates = labels["bboxes"]
elif self.task == "segment":
elif self.task in {"segment", "obb"}: # Segment and OBB use segments. OBB segments are normalized xyxyxyxy
coordinates = [x.flatten() for x in labels["segments"]]
elif self.task == "pose":
n, nk, nd = labels["keypoints"].shape
coordinates = np.concatenate((labels["bboxes"], labels["keypoints"].reshape(n, nk * nd)), 1)
else:
raise ValueError("Undefined dataset task.")
raise ValueError(f"Undefined dataset task={self.task}.")
zipped = zip(labels["cls"], coordinates)
return [[int(c[0]), *(round(float(x), 4) for x in points)] for c, points in zipped]

10
ultralytics/hub/__init__.py
View file

@ -106,22 +106,26 @@ def get_export(model_id="", format="torchscript"):
return r.json()
def check_dataset(path="", task="detect"):
def check_dataset(path: str, task: str) -> None:
"""
Function for error-checking HUB dataset Zip file before upload. It checks a dataset for errors before it is uploaded
to the HUB. Usage examples are given below.
Args:
path (str, optional): Path to data.zip (with data.yaml inside data.zip). Defaults to ''.
task (str, optional): Dataset task. Options are 'detect', 'segment', 'pose', 'classify'. Defaults to 'detect'.
path (str): Path to data.zip (with data.yaml inside data.zip).
task (str): Dataset task. Options are 'detect', 'segment', 'pose', 'classify', 'obb'.
Example:
Download *.zip files from https://github.com/ultralytics/hub/tree/main/example_datasets
i.e. https://github.com/ultralytics/hub/raw/main/example_datasets/coco8.zip for coco8.zip.
```python
from ultralytics.hub import check_dataset
check_dataset('path/to/coco8.zip', task='detect') # detect dataset
check_dataset('path/to/coco8-seg.zip', task='segment') # segment dataset
check_dataset('path/to/coco8-pose.zip', task='pose') # pose dataset
check_dataset('path/to/dota8.zip', task='obb') # OBB dataset
check_dataset('path/to/imagenet10.zip', task='classify') # classification dataset
```
"""
HUBDatasetStats(path=path, task=task).get_json()

33
ultralytics/utils/plotting.py
View file

@ -1105,23 +1105,24 @@ def feature_visualization(x, module_type, stage, n=32, save_dir=Path("runs/detec
n (int, optional): Maximum number of feature maps to plot. Defaults to 32.
save_dir (Path, optional): Directory to save results. Defaults to Path('runs/detect/exp').
"""
for m in ["Detect", "Pose", "Segment"]:
for m in {"Detect", "Segment", "Pose", "Classify", "OBB", "RTDETRDecoder"}: # all model heads
if m in module_type:
return
_, channels, height, width = x.shape # batch, channels, height, width
if height > 1 and width > 1:
f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
if isinstance(x, torch.Tensor):
_, channels, height, width = x.shape # batch, channels, height, width
if height > 1 and width > 1:
f = save_dir / f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
n = min(n, channels) # number of plots
_, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
ax = ax.ravel()
plt.subplots_adjust(wspace=0.05, hspace=0.05)
for i in range(n):
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
ax[i].axis("off")
blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
n = min(n, channels) # number of plots
_, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
ax = ax.ravel()
plt.subplots_adjust(wspace=0.05, hspace=0.05)
for i in range(n):
ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
ax[i].axis("off")
LOGGER.info(f"Saving {f}... ({n}/{channels})")
plt.savefig(f, dpi=300, bbox_inches="tight")
plt.close()
np.save(str(f.with_suffix(".npy")), x[0].cpu().numpy()) # npy save
LOGGER.info(f"Saving {f}... ({n}/{channels})")
plt.savefig(f, dpi=300, bbox_inches="tight")
plt.close()
np.save(str(f.with_suffix(".npy")), x[0].cpu().numpy()) # npy save