YOLOv5 segmentation model support

.github/workflows/ci-testing.yml

@@ -15,6 +15,7 @@ jobs:
   Benchmarks:
     runs-on: ${{ matrix.os }}
     strategy:
+      fail-fast: false
       matrix:
         os: [ ubuntu-latest ]
         python-version: [ '3.9' ]  # requires python<=3.9
@@ -37,9 +38,12 @@ jobs:
           python --version
           pip --version
           pip list
-      - name: Run benchmarks
+      - name: Benchmark DetectionModel
+        run: |
+          python benchmarks.py --data coco128.yaml --weights ${{ matrix.model }}.pt --img 320 --hard-fail 0.29
+      - name: Benchmark SegmentationModel
         run: |
-          python utils/benchmarks.py --weights ${{ matrix.model }}.pt --img 320 --hard-fail 0.29
+          python benchmarks.py --data coco128-seg.yaml --weights ${{ matrix.model }}-seg.pt --img 320
 
   Tests:
     timeout-minutes: 60
@@ -126,6 +130,20 @@ jobs:
               model(im)  # warmup, build grids for trace
               torch.jit.trace(model, [im])
           EOF
+      - name: Test segmentation
+        shell: bash  # for Windows compatibility
+        run: |
+          m=${{ matrix.model }}-seg  # official weights
+          b=runs/train-seg/exp/weights/best  # best.pt checkpoint
+          python segment/train.py --imgsz 64 --batch 32 --weights $m.pt --cfg $m.yaml --epochs 1 --device cpu  # train
+          python segment/train.py --imgsz 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device cpu  # train
+          for d in cpu; do  # devices
+            for w in $m $b; do  # weights
+              python segment/val.py --imgsz 64 --batch 32 --weights $w.pt --device $d  # val
+              python segment/predict.py --imgsz 64 --weights $w.pt --device $d  # predict
+              python export.py --weights $w.pt --img 64 --include torchscript --device $d  # export
+            done
+          done
       - name: Test classification
         shell: bash  # for Windows compatibility
         run: |

utils/benchmarks.py → benchmarks.py

@@ -34,16 +34,19 @@
 import pandas as pd
 
 FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
+ROOT = FILE.parents[0]  # YOLOv5 root directory
 if str(ROOT) not in sys.path:
     sys.path.append(str(ROOT))  # add ROOT to PATH
 # ROOT = ROOT.relative_to(Path.cwd())  # relative
 
 import export
-import val
+from models.experimental import attempt_load
+from models.yolo import SegmentationModel
+from segment.val import run as val_seg
 from utils import notebook_init
 from utils.general import LOGGER, check_yaml, file_size, print_args
 from utils.torch_utils import select_device
+from val import run as val_det
 
 
 def run(
@@ -59,6 +62,7 @@ def run(
 ):
     y, t = [], time.time()
     device = select_device(device)
+    model_type = type(attempt_load(weights, fuse=False))  # DetectionModel, SegmentationModel, etc.
     for i, (name, f, suffix, cpu, gpu) in export.export_formats().iterrows():  # index, (name, file, suffix, CPU, GPU)
         try:
             assert i not in (9, 10, 11), 'inference not supported'  # Edge TPU, TF.js and Paddle are unsupported
@@ -76,10 +80,14 @@ def run(
             assert suffix in str(w), 'export failed'
 
             # Validate
-            result = val.run(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
-            metrics = result[0]  # metrics (mp, mr, map50, map, *losses(box, obj, cls))
-            speeds = result[2]  # times (preprocess, inference, postprocess)
-            y.append([name, round(file_size(w), 1), round(metrics[3], 4), round(speeds[1], 2)])  # MB, mAP, t_inference
+            if model_type == SegmentationModel:
+                result = val_seg(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
+                metric = result[0][7]  # (box(p, r, map50, map), mask(p, r, map50, map), *loss(box, obj, cls))
+            else:  # DetectionModel:
+                result = val_det(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
+                metric = result[0][3]  # (p, r, map50, map, *loss(box, obj, cls))
+            speed = result[2][1]  # times (preprocess, inference, postprocess)
+            y.append([name, round(file_size(w), 1), round(metric, 4), round(speed, 2)])  # MB, mAP, t_inference
         except Exception as e:
             if hard_fail:
                 assert type(e) is AssertionError, f'Benchmark --hard-fail for {name}: {e}'

data/coco128-seg.yaml

@@ -0,0 +1,101 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+# COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
+# Example usage: python train.py --data coco128.yaml
+# parent
+# ├── yolov5
+# └── datasets
+#     └── coco128-seg  ← downloads here (7 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/coco128-seg  # dataset root dir
+train: images/train2017  # train images (relative to 'path') 128 images
+val: images/train2017  # val images (relative to 'path') 128 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/coco128-seg.zip

detect.py

@@ -149,8 +149,8 @@ def run(
                 det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
 
                 # Print results
-                for c in det[:, -1].unique():
-                    n = (det[:, -1] == c).sum()  # detections per class
+                for c in det[:, 5].unique():
+                    n = (det[:, 5] == c).sum()  # detections per class
                     s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
 
                 # Write results

models/common.py

@@ -375,7 +375,6 @@ def __init__(self, weights='yolov5s.pt', device=torch.device('cpu'), dnn=False,
             if batch_dim.is_static:
                 batch_size = batch_dim.get_length()
             executable_network = ie.compile_model(network, device_name="CPU")  # device_name="MYRIAD" for Intel NCS2
-            output_layer = next(iter(executable_network.outputs))
             stride, names = self._load_metadata(Path(w).with_suffix('.yaml'))  # load metadata
         elif engine:  # TensorRT
             LOGGER.info(f'Loading {w} for TensorRT inference...')
@@ -491,7 +490,7 @@ def forward(self, im, augment=False, visualize=False):
             y = self.session.run(self.output_names, {self.session.get_inputs()[0].name: im})
         elif self.xml:  # OpenVINO
             im = im.cpu().numpy()  # FP32
-            y = self.executable_network([im])[self.output_layer]
+            y = list(self.executable_network([im]).values())
         elif self.engine:  # TensorRT
             if self.dynamic and im.shape != self.bindings['images'].shape:
                 i_in, i_out = (self.model.get_binding_index(x) for x in ('images', 'output'))
@@ -786,8 +785,21 @@ def __str__(self):
         return ''
 
 
+class Proto(nn.Module):
+    # YOLOv5 mask Proto module for segmentation models
+    def __init__(self, c1, c_=256, c2=32):  # ch_in, number of protos, number of masks
+        super().__init__()
+        self.cv1 = Conv(c1, c_, k=3)
+        self.upsample = nn.Upsample(scale_factor=2, mode='nearest')
+        self.cv2 = Conv(c_, c_, k=3)
+        self.cv3 = Conv(c_, c2)
+
+    def forward(self, x):
+        return self.cv3(self.cv2(self.upsample(self.cv1(x))))
+
+
 class Classify(nn.Module):
-    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    # YOLOv5 classification head, i.e. x(b,c1,20,20) to x(b,c2)
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
         super().__init__()
         c_ = 1280  # efficientnet_b0 size

models/segment/yolov5l-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5m-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]

models/segment/yolov5n-seg.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]],  # Detect(P3, P4, P5)
+  ]