COCO8 and COCO8-seg Pytest and CI updates (#307)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: RangiLyu <lyuchqi@gmail.com>

.github/workflows/ci.yaml

@@ -8,8 +8,8 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
-  # schedule:
-  #   - cron: '0 0 * * *'  # runs at 00:00 UTC every day
+  schedule:
+    - cron: '0 0 * * *'  # runs at 00:00 UTC every day
 
 jobs:
   Tests:
@@ -54,7 +54,7 @@ jobs:
               pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu
           fi
           # pip install ultralytics (production)
-          pip install .
+          pip install -e . pytest
         shell: bash  # for Windows compatibility
       - name: Check environment
         run: |
@@ -78,21 +78,21 @@ jobs:
           from ultralytics import hub, yolo
           key = os.environ['APIKEY']
           print(ultralytics.__version__)
-          # ultralytics.checks()
+          ultralytics.checks()
           # ultralytics.reset_model(key)  # reset trained model
           # ultralytics.start(key)  # train model
       - name: Test detection
         shell: bash  # for Windows compatibility
         run: |
-          yolo task=detect mode=train model=yolov8n.yaml data=coco128.yaml epochs=1 imgsz=32
+          yolo task=detect mode=train model=yolov8n.yaml data=coco8.yaml epochs=1 imgsz=32
           yolo task=detect mode=val model=runs/detect/train/weights/last.pt imgsz=32
           yolo task=detect mode=predict model=runs/detect/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
           yolo mode=export model=runs/detect/train/weights/last.pt imgsz=32 format=torchscript
       - name: Test segmentation
         shell: bash  # for Windows compatibility
         run: |
-          yolo task=segment mode=train model=yolov8n-seg.yaml data=coco128-seg.yaml epochs=1 imgsz=32
-          yolo task=segment mode=val model=runs/segment/train/weights/last.pt data=coco128-seg.yaml imgsz=32
+          yolo task=segment mode=train model=yolov8n-seg.yaml data=coco8-seg.yaml epochs=1 imgsz=32
+          yolo task=segment mode=val model=runs/segment/train/weights/last.pt data=coco8-seg.yaml imgsz=32
           yolo task=segment mode=predict model=runs/segment/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
           yolo mode=export model=runs/segment/train/weights/last.pt imgsz=32 format=torchscript
       - name: Test classification
@@ -102,3 +102,6 @@ jobs:
           yolo task=classify mode=val model=runs/classify/train/weights/last.pt data=mnist160 imgsz=32
           yolo task=classify mode=predict model=runs/classify/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg
           yolo mode=export model=runs/classify/train/weights/last.pt imgsz=32 format=torchscript
+      - name: Pytest tests
+        shell: bash  # for Windows compatibility
+        run: pytest tests

.gitignore

@@ -148,3 +148,4 @@ wandb/
 *_saved_model/
 *_web_model/
 *_openvino_model/
+*_paddle_model/

docs/index.md

@@ -10,11 +10,8 @@
     <a href="https://colab.research.google.com/github/ultralytics/ultralytics/blob/main/examples/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
     <a href="https://www.kaggle.com/ultralytics/yolov8"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
 <br>
-<br>
 </div>
 
-# Welcome to Ultralytics YOLOv8
-
 Welcome to the Ultralytics YOLOv8 documentation landing
 page! [Ultralytics YOLOv8](https://github.com/ultralytics/ultralytics) is the latest version of the YOLO (You Only Look
 Once) object detection and image segmentation model developed by [Ultralytics](https://ultralytics.com). This page

mkdocs.yml

@@ -1,4 +1,4 @@
-site_name: Ultralytics Docs
+site_name: Ultralytics YOLOv8 Docs
 repo_url: https://github.com/ultralytics/ultralytics
 edit_uri: https://github.com/ultralytics/ultralytics/tree/main/docs
 repo_name: ultralytics/ultralytics
@@ -6,7 +6,7 @@ repo_name: ultralytics/ultralytics
 theme:
   name: "material"
   logo: https://github.com/ultralytics/assets/raw/main/logo/Ultralytics-logomark-white.png
-  favicon: assets/favicon.ico
+  favicon: https://github.com/ultralytics/assets/raw/main/logo/favicon-yolo.ico
   font:
     text: Roboto
 
@@ -75,6 +75,7 @@ plugins:
 
 # Primary navigation
 nav:
+  - Home: index.md
   - Quickstart: quickstart.md
   - Tasks:
       - Detection: tasks/detection.md

setup.py

@@ -8,13 +8,13 @@ from setuptools import find_packages, setup
 
 # Settings
 FILE = Path(__file__).resolve()
-ROOT = FILE.parent  # root directory
-README = (ROOT / "README.md").read_text(encoding="utf-8")
-REQUIREMENTS = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements((ROOT / 'requirements.txt').read_text())]
+PARENT = FILE.parent  # root directory
+README = (PARENT / "README.md").read_text(encoding="utf-8")
+REQUIREMENTS = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements((PARENT / 'requirements.txt').read_text())]
 
 
 def get_version():
-    file = ROOT / 'ultralytics/__init__.py'
+    file = PARENT / 'ultralytics/__init__.py'
     return re.search(r'^__version__ = [\'"]([^\'"]*)[\'"]', file.read_text(), re.M)[1]
 
 

tests/test_cli.py

@@ -15,11 +15,11 @@ def test_checks():
 
 # Train checks ---------------------------------------------------------------------------------------------------------
 def test_train_det():
-    os.system(f'yolo mode=train task=detect model={CFG}.yaml data=coco128.yaml imgsz=32 epochs=1')
+    os.system(f'yolo mode=train task=detect model={CFG}.yaml data=coco8.yaml imgsz=32 epochs=1')
 
 
 def test_train_seg():
-    os.system(f'yolo mode=train task=segment model={CFG}-seg.yaml data=coco128-seg.yaml imgsz=32 epochs=1')
+    os.system(f'yolo mode=train task=segment model={CFG}-seg.yaml data=coco8-seg.yaml imgsz=32 epochs=1')
 
 
 def test_train_cls():
@@ -28,11 +28,11 @@ def test_train_cls():
 
 # Val checks -----------------------------------------------------------------------------------------------------------
 def test_val_detect():
-    os.system(f'yolo mode=val task=detect model={MODEL}.pt data=coco128.yaml imgsz=32 epochs=1')
+    os.system(f'yolo mode=val task=detect model={MODEL}.pt data=coco8.yaml imgsz=32 epochs=1')
 
 
 def test_val_segment():
-    os.system(f'yolo mode=val task=segment model={MODEL}-seg.pt data=coco128-seg.yaml imgsz=32 epochs=1')
+    os.system(f'yolo mode=val task=segment model={MODEL}-seg.pt data=coco8-seg.yaml imgsz=32 epochs=1')
 
 
 def test_val_classify():

tests/test_engine.py

@@ -1,6 +1,5 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
 
-from ultralytics import YOLO
 from ultralytics.yolo.configs import get_config
 from ultralytics.yolo.utils import DEFAULT_CONFIG, ROOT
 from ultralytics.yolo.v8 import classify, detect, segment
@@ -13,9 +12,10 @@ SOURCE = ROOT / "assets"
 
 
 def test_detect():
-    overrides = {"data": "coco128.yaml", "model": CFG_DET, "imgsz": 32, "epochs": 1, "save": False}
-    CFG.data = "coco128.yaml"
-    # trainer
+    overrides = {"data": "coco8.yaml", "model": CFG_DET, "imgsz": 32, "epochs": 1, "save": False}
+    CFG.data = "coco8.yaml"
+
+    # Trainer
     trainer = detect.DetectionTrainer(overrides=overrides)
     trainer.train()
     trained_model = trainer.best
@@ -24,12 +24,10 @@ def test_detect():
     val = detect.DetectionValidator(args=CFG)
     val(model=trained_model)
 
-    # predictor
-    pred = detect.DetectionPredictor(overrides={"imgsz": [640, 640]})
-    i = 0
-    for _ in pred(source=SOURCE, model="yolov8n.pt", return_outputs=True):
-        i += 1
-    assert i == 2, "predictor test failed"
+    # Predictor
+    pred = detect.DetectionPredictor(overrides={"imgsz": [64, 64]})
+    result = pred(source=SOURCE, model="yolov8n.pt", return_outputs=True)
+    assert len(list(result)), "predictor test failed"
 
     overrides["resume"] = trainer.last
     trainer = detect.DetectionTrainer(overrides=overrides)
@@ -43,11 +41,11 @@ def test_detect():
 
 
 def test_segment():
-    overrides = {"data": "coco128-seg.yaml", "model": CFG_SEG, "imgsz": 32, "epochs": 1, "save": False}
-    CFG.data = "coco128-seg.yaml"
+    overrides = {"data": "coco8-seg.yaml", "model": CFG_SEG, "imgsz": 32, "epochs": 1, "save": False}
+    CFG.data = "coco8-seg.yaml"
     CFG.v5loader = False
+    # YOLO(CFG_SEG).train(**overrides)  # works
 
-    # YOLO(CFG_SEG).train(**overrides) # This works
     # trainer
     trainer = segment.SegmentationTrainer(overrides=overrides)
     trainer.train()
@@ -57,14 +55,12 @@ def test_segment():
     val = segment.SegmentationValidator(args=CFG)
     val(model=trained_model)
 
-    # predictor
-    pred = segment.SegmentationPredictor(overrides={"imgsz": [640, 640]})
-    i = 0
-    for _ in pred(source=SOURCE, model="yolov8n-seg.pt", return_outputs=True):
-        i += 1
-    assert i == 2, "predictor test failed"
+    # Predictor
+    pred = segment.SegmentationPredictor(overrides={"imgsz": [64, 64]})
+    result = pred(source=SOURCE, model="yolov8n-seg.pt", return_outputs=True)
+    assert len(list(result)) == 2, "predictor test failed"
 
-    # test resume
+    # Test resume
     overrides["resume"] = trainer.last
     trainer = segment.SegmentationTrainer(overrides=overrides)
     try:
@@ -81,8 +77,9 @@ def test_classify():
     CFG.data = "mnist160"
     CFG.imgsz = 32
     CFG.batch = 64
-    # YOLO(CFG_SEG).train(**overrides) # This works
-    # trainer
+    # YOLO(CFG_SEG).train(**overrides)  # works
+
+    # Trainer
     trainer = classify.ClassificationTrainer(overrides=overrides)
     trainer.train()
     trained_model = trainer.best
@@ -91,9 +88,7 @@ def test_classify():
     val = classify.ClassificationValidator(args=CFG)
     val(model=trained_model)
 
-    # predictor
-    pred = classify.ClassificationPredictor(overrides={"imgsz": [640, 640]})
-    i = 0
-    for _ in pred(source=SOURCE, model=trained_model, return_outputs=True):
-        i += 1
-    assert i == 2, "predictor test failed"
+    # Predictor
+    pred = classify.ClassificationPredictor(overrides={"imgsz": [64, 64]})
+    result = pred(source=SOURCE, model=trained_model, return_outputs=True)
+    assert len(list(result)) == 2, "predictor test failed"

tests/test_python.py

@@ -37,18 +37,18 @@ def test_predict_dir():
 
 def test_val():
     model = YOLO(MODEL)
-    model.val(data="coco128.yaml", imgsz=32)
+    model.val(data="coco8.yaml", imgsz=32)
 
 
 def test_train_scratch():
     model = YOLO(CFG)
-    model.train(data="coco128.yaml", epochs=1, imgsz=32)
+    model.train(data="coco8.yaml", epochs=1, imgsz=32)
     model(SOURCE)
 
 
 def test_train_pretrained():
     model = YOLO(MODEL)
-    model.train(data="coco128.yaml", epochs=1, imgsz=32)
+    model.train(data="coco8.yaml", epochs=1, imgsz=32)
     model(SOURCE)
 
 
@@ -102,7 +102,7 @@ def test_all_model_yamls():
 
 def test_workflow():
     model = YOLO(MODEL)
-    model.train(data="coco128.yaml", epochs=1, imgsz=32)
+    model.train(data="coco8.yaml", epochs=1, imgsz=32)
     model.val()
     model.predict(SOURCE)
     model.export(format="onnx", opset=12)  # export a model to ONNX format

ultralytics/nn/modules.py

@@ -82,7 +82,7 @@ class ConvTranspose(nn.Module):
 
 
 class DFL(nn.Module):
-    # DFL module
+    # Integral module of Distribution Focal Loss (DFL) proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391
     def __init__(self, c1=16):
         super().__init__()
         self.conv = nn.Conv2d(c1, 1, 1, bias=False).requires_grad_(False)

ultralytics/yolo/data/datasets/coco8-seg.yaml

@@ -0,0 +1,101 @@
+# Ultralytics YOLO 🚀, GPL-3.0 license
+# COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics
+# Example usage: python train.py --data coco8-seg.yaml
+# parent
+# ├── yolov5
+# └── datasets
+#     └── coco8-seg  ← downloads here (1 MB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco8-seg  # dataset root dir
+train: images/train  # train images (relative to 'path') 4 images
+val: images/val  # val images (relative to 'path') 4 images
+test:  # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+
+# Download script/URL (optional)
+download: https://ultralytics.com/assets/coco8-seg.zip

ultralytics/yolo/data/datasets/coco8.yaml

@@ -0,0 +1,101 @@
+# Ultralytics YOLO 🚀, GPL-3.0 license
+# COCO8 dataset (first 8 images from COCO train2017) by Ultralytics
+# Example usage: python train.py --data coco8.yaml
+# parent
+# ├── yolov5
+# └── datasets
+#     └── coco8  ← downloads here (1 MB)
+
+
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco8  # dataset root dir
+train: images/train  # train images (relative to 'path') 4 images
+val: images/val  # val images (relative to 'path') 4 images
+test:  # test images (optional)
+
+# Classes
+names:
+  0: person
+  1: bicycle
+  2: car
+  3: motorcycle
+  4: airplane
+  5: bus
+  6: train
+  7: truck
+  8: boat
+  9: traffic light
+  10: fire hydrant
+  11: stop sign
+  12: parking meter
+  13: bench
+  14: bird
+  15: cat
+  16: dog
+  17: horse
+  18: sheep
+  19: cow
+  20: elephant
+  21: bear
+  22: zebra
+  23: giraffe
+  24: backpack
+  25: umbrella
+  26: handbag
+  27: tie
+  28: suitcase
+  29: frisbee
+  30: skis
+  31: snowboard
+  32: sports ball
+  33: kite
+  34: baseball bat
+  35: baseball glove
+  36: skateboard
+  37: surfboard
+  38: tennis racket
+  39: bottle
+  40: wine glass
+  41: cup
+  42: fork
+  43: knife
+  44: spoon
+  45: bowl
+  46: banana
+  47: apple
+  48: sandwich
+  49: orange
+  50: broccoli
+  51: carrot
+  52: hot dog
+  53: pizza
+  54: donut
+  55: cake
+  56: chair
+  57: couch
+  58: potted plant
+  59: bed
+  60: dining table
+  61: toilet
+  62: tv
+  63: laptop
+  64: mouse
+  65: remote
+  66: keyboard
+  67: cell phone
+  68: microwave
+  69: oven
+  70: toaster
+  71: sink
+  72: refrigerator
+  73: book
+  74: clock
+  75: vase
+  76: scissors
+  77: teddy bear
+  78: hair drier
+  79: toothbrush
+
+
+# Download script/URL (optional)
+download: https://ultralytics.com/assets/coco8.zip

ultralytics/yolo/utils/loss.py

@@ -47,6 +47,7 @@ class BboxLoss(nn.Module):
     @staticmethod
     def _df_loss(pred_dist, target):
         # Return sum of left and right DFL losses
+        # Distribution Focal Loss (DFL) proposed in Generalized Focal Loss https://ieeexplore.ieee.org/document/9792391
         tl = target.long()  # target left
         tr = tl + 1  # target right
         wl = tr - target  # weight left

ultralytics/yolo/v8/__init__.py

@@ -1,11 +1,6 @@
 # Ultralytics YOLO 🚀, GPL-3.0 license
 
-from pathlib import Path
-
+from ultralytics.yolo.configs import hydra_patch  # noqa (patch hydra cli)
 from ultralytics.yolo.v8 import classify, detect, segment
 
-ROOT = Path(__file__).parents[0]  # yolov8 ROOT
-
 __all__ = ["classify", "segment", "detect"]
-
-from ultralytics.yolo.configs import hydra_patch  # noqa (patch hydra cli)