update to ultralytics/yolov5 13.12.22 (#170)

* init update * update val * update export * update benchmarks * update detect * update train * update utils * update segment utils * update wandb utils * update clearml utils * update data * update models * update version * update classify * update segment * fix val * fix val * fix val half * fix val half
fcakyon · Dec 13, 2022 · bba5f85 · bba5f85
1 parent 9defab4
commit bba5f85
Show file tree

Hide file tree

Showing 33 changed files with 409 additions and 279 deletions.
diff --git a/README.md b/README.md
@@ -25,7 +25,7 @@ You can finally install <a href="https://github.com/ultralytics/yolov5">YOLOv5 o
 </div>
 
 <br>
-This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/tree/8236d8818bca21c692d5c4508fee2af835ec1dbe">at this commit</a> plus:
+This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/commit/357cde9ee7da13ba3095995488c5a23631467f1a">at this commit</a> plus:
 <br>
 1. Easy installation via pip: `pip install yolov5`
 <br>

diff --git a/requirements.txt b/requirements.txt
@@ -1,29 +1,33 @@
-# YOLOv5 requirements
+# YOLOv5 🚀 requirements
 # Usage: pip install -r requirements.txt
 
-# Base ----------------------------------------
+# Base ------------------------------------------------------------------------
+gitpython
+ipython  # interactive notebook
 matplotlib>=3.2.2
 numpy>=1.18.5
 opencv-python>=4.1.1
 Pillow>=7.1.2
+psutil  # system resources
 PyYAML>=5.3.1
 requests>=2.23.0
 scipy>=1.4.1
-torch>=1.7.0  # see https://pytorch.org/get-started/locally/ (recommended)
+thop>=0.1.1  # FLOPs computation
+torch>=1.7.0  # see https://pytorch.org/get-started/locally (recommended)
 torchvision>=0.8.1
 tqdm>=4.64.0
 # protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012
 
-# Logging -------------------------------------
+# Logging ---------------------------------------------------------------------
 tensorboard>=2.4.1
-# clearml
+# clearml>=1.2.0
 # comet
 
-# Plotting ------------------------------------
+# Plotting --------------------------------------------------------------------
 pandas>=1.1.4
 seaborn>=0.11.0
 
-# Export --------------------------------------
+# Export ----------------------------------------------------------------------
 # coremltools>=6.0  # CoreML export
 # onnx>=1.9.0  # ONNX export
 # onnx-simplifier>=0.4.1  # ONNX simplifier
@@ -34,17 +38,15 @@ seaborn>=0.11.0
 # tensorflowjs>=3.9.0  # TF.js export
 # openvino-dev  # OpenVINO export
 
-# Deploy --------------------------------------
+# Deploy ----------------------------------------------------------------------
 # tritonclient[all]~=2.24.0
 
-# Extras --------------------------------------
-ipython  # interactive notebook
-psutil  # system utilization
-thop>=0.1.1  # FLOPs computation
+# Extras ----------------------------------------------------------------------
 # mss  # screenshots
 # albumentations>=1.0.3
 # pycocotools>=2.0  # COCO mAP
 # roboflow
+# ultralytics  # HUB https://hub.ultralytics.com
 
 # CLI
 fire

diff --git a/yolov5/__init__.py b/yolov5/__init__.py
@@ -1,4 +1,4 @@
 from yolov5.helpers import YOLOv5
 from yolov5.helpers import load_model as load
 
-__version__ = "6.2.3"
+__version__ = "7.0.0"
diff --git a/yolov5/benchmarks.py b/yolov5/benchmarks.py
@@ -163,7 +163,7 @@ def run_cli(**kwargs):
 
 def parse_opt():
     parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
+    parser.add_argument('--weights', type=str, default='yolov5s.pt', help='weights path')
     parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
     parser.add_argument('--batch-size', type=int, default=1, help='batch size')
     parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')

diff --git a/yolov5/classify/predict.py b/yolov5/classify/predict.py
@@ -6,7 +6,10 @@
     $ python classify/predict.py --weights yolov5s-cls.pt --source 0                               # webcam
                                                                    img.jpg                         # image
                                                                    vid.mp4                         # video
+                                                                   screen                          # screenshot
                                                                    path/                           # directory
+                                                                   list.txt                        # list of images
+                                                                   list.streams                    # list of streams
                                                                    'path/*.jpg'                    # glob
                                                                    'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                                    'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
@@ -63,7 +66,7 @@ def run(
         augment=False,  # augmented inference
         visualize=False,  # visualize features
         update=False,  # update all models
-        project=ROOT / 'runs/predict-cls',  # save results to project/name
+        project='runs/predict-cls',  # save results to project/name
         name='exp',  # save results to project/name
         exist_ok=False,  # existing project/name ok, do not increment
         half=False,  # use FP16 half-precision inference
@@ -74,7 +77,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download
@@ -205,7 +208,7 @@ def parse_opt():
     parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[224], help='inference size h,w')
     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
     parser.add_argument('--view-img', action='store_true', help='show results')
-    parser.add_argument('--save-txt', action='store_false', help='save results to *.txt')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
     parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
     parser.add_argument('--augment', action='store_true', help='augmented inference')
     parser.add_argument('--visualize', action='store_true', help='visualize features')

diff --git a/yolov5/classify/train.py b/yolov5/classify/train.py
@@ -40,8 +40,8 @@
 from yolov5.models.experimental import attempt_load
 from yolov5.models.yolo import ClassificationModel, DetectionModel
 from yolov5.utils.dataloaders import create_classification_dataloader
-from yolov5.utils.general import (DATASETS_DIR, LOGGER, WorkingDirectory, check_git_status, check_requirements, colorstr,
-                           download, increment_path, init_seeds, print_args, yaml_save)
+from yolov5.utils.general import (DATASETS_DIR, LOGGER, TQDM_BAR_FORMAT, WorkingDirectory, check_git_info, check_git_status,
+                           check_requirements, colorstr, download, increment_path, init_seeds, print_args, yaml_save)
 from yolov5.utils.loggers import GenericLogger
 from yolov5.utils.plots import imshow_cls
 from yolov5.utils.torch_utils import (ModelEMA, model_info, reshape_classifier_output, select_device, smart_DDP,
@@ -50,6 +50,7 @@
 LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
 RANK = int(os.getenv('RANK', -1))
 WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
+#GIT_INFO = check_git_info()
 
 
 def train(opt, device):
@@ -174,7 +175,7 @@ def train(opt, device):
             trainloader.sampler.set_epoch(epoch)
         pbar = enumerate(trainloader)
         if RANK in {-1, 0}:
-            pbar = tqdm(enumerate(trainloader), total=len(trainloader), bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')
+            pbar = tqdm(enumerate(trainloader), total=len(trainloader), bar_format=TQDM_BAR_FORMAT)
         for i, (images, labels) in pbar:  # progress bar
             images, labels = images.to(device, non_blocking=True), labels.to(device)
 

diff --git a/yolov5/classify/val.py b/yolov5/classify/val.py
@@ -36,7 +36,8 @@
 
 from yolov5.models.common import DetectMultiBackend
 from yolov5.utils.dataloaders import create_classification_dataloader
-from yolov5.utils.general import LOGGER, Profile, check_img_size, check_requirements, colorstr, increment_path, print_args
+from yolov5.utils.general import (LOGGER, TQDM_BAR_FORMAT, Profile, check_img_size, check_requirements, colorstr,
+                           increment_path, print_args)
 from yolov5.utils.torch_utils import select_device, smart_inference_mode
 
 
@@ -112,7 +113,7 @@ def run(
     n = len(dataloader)  # number of batches
     action = 'validating' if dataloader.dataset.root.stem == 'val' else 'testing'
     desc = f"{pbar.desc[:-36]}{action:>36}" if pbar else f"{action}"
-    bar = tqdm(dataloader, desc, n, not training, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}', position=0)
+    bar = tqdm(dataloader, desc, n, not training, bar_format=TQDM_BAR_FORMAT, position=0)
     with torch.cuda.amp.autocast(enabled=device.type != 'cpu'):
         for images, labels in bar:
             with dt[0]:

diff --git a/yolov5/data/scripts/download_weights.sh b/yolov5/data/scripts/download_weights.sh
@@ -9,13 +9,14 @@
 #     └── ...
 
 python - <<EOF
-from yolov5.utils.downloads import attempt_download
+from utils.downloads import attempt_download
 
-p5 = ['n', 's', 'm', 'l', 'x']  # P5 models
+p5 = list('nsmlx')  # P5 models
 p6 = [f'{x}6' for x in p5]  # P6 models
 cls = [f'{x}-cls' for x in p5]  # classification models
+seg = [f'{x}-seg' for x in p5]  # classification models
 
-for x in p5 + p6 + cls:
+for x in p5 + p6 + cls + seg:
     attempt_download(f'weights/yolov5{x}.pt')
 
 EOF
diff --git a/yolov5/data/scripts/get_coco.sh b/yolov5/data/scripts/get_coco.sh
@@ -30,7 +30,7 @@ url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
 if [ "$segments" == "true" ]; then
   f='coco2017labels-segments.zip' # 168 MB
 else
-  f='coco2017labels.zip' # 168 MB
+  f='coco2017labels.zip' # 46 MB
 fi
 echo 'Downloading' $url$f ' ...'
 curl -L $url$f -o $f -# && unzip -q $f -d $d && rm $f &

diff --git a/yolov5/detect.py b/yolov5/detect.py
@@ -4,25 +4,28 @@
 
 Usage - sources:
     $ yolov5 detect --weights yolov5s.pt --source 0                               # webcam
-                                            img.jpg                             # image
-                                            vid.mp4                             # video
-                                            path/                               # directory
-                                            'path/*.jpg'                        # glob
-                                            'https://youtu.be/Zgi9g1ksQHc'      # YouTube
-                                            'rtsp://example.com/media.mp4'      # RTSP, RTMP, HTTP stream
+                                                     img.jpg                         # image
+                                                     vid.mp4                         # video
+                                                     screen                          # screenshot
+                                                     path/                           # directory
+                                                     list.txt                        # list of images
+                                                     list.streams                    # list of streams
+                                                     'path/*.jpg'                    # glob
+                                                     'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                     'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
 
 Usage - formats:
     $ yolov5 detect --weights yolov5s.pt                 # PyTorch
-                                yolov5s.torchscript        # TorchScript
-                                yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
-                                yolov5s.xml                # OpenVINO
-                                yolov5s.engine             # TensorRT
-                                yolov5s.mlmodel            # CoreML (macOS-only)
-                                yolov5s_saved_model        # TensorFlow SavedModel
-                                yolov5s.pb                 # TensorFlow GraphDef
-                                yolov5s.tflite             # TensorFlow Lite
-                                yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
-                                yolov5s_paddle_model       # PaddlePaddle
+                                 yolov5s.torchscript        # TorchScript
+                                 yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                 yolov5s_openvino_model     # OpenVINO
+                                 yolov5s.engine             # TensorRT
+                                 yolov5s.mlmodel            # CoreML (macOS-only)
+                                 yolov5s_saved_model        # TensorFlow SavedModel
+                                 yolov5s.pb                 # TensorFlow GraphDef
+                                 yolov5s.tflite             # TensorFlow Lite
+                                 yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+                                 yolov5s_paddle_model       # PaddlePaddle
 """
 
 import argparse
@@ -82,7 +85,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download

diff --git a/yolov5/export.py b/yolov5/export.py
@@ -25,10 +25,10 @@
     $ yolov5 export --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
 
 Inference:
-    $ yolov5 export --weights yolov5s.pt                 # PyTorch
+    $ yolov5 detect --weights yolov5s.pt                 # PyTorch
                                  yolov5s.torchscript        # TorchScript
                                  yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
-                                 yolov5s.xml                # OpenVINO
+                                 yolov5s_openvino_model     # OpenVINO
                                  yolov5s.engine             # TensorRT
                                  yolov5s.mlmodel            # CoreML (macOS-only)
                                  yolov5s_saved_model        # TensorFlow SavedModel
@@ -153,7 +153,7 @@ def export_onnx(model, im, file, opset, dynamic, simplify, prefix=colorstr('ONNX
         f,
         verbose=False,
         opset_version=opset,
-        do_constant_folding=True,
+        do_constant_folding=True,  # WARNING: DNN inference with torch>=1.12 may require do_constant_folding=False
         input_names=['images'],
         output_names=output_names,
         dynamic_axes=dynamic or None)
@@ -607,15 +607,16 @@ def run(
     f = [str(x) for x in f if x]  # filter out '' and None
     if any(f):
         cls, det, seg = (isinstance(model, x) for x in (ClassificationModel, DetectionModel, SegmentationModel))  # type
+        det &= not seg  # segmentation models inherit from SegmentationModel(DetectionModel)
         dir = Path('segment' if seg else 'classify' if cls else '')
         h = '--half' if half else ''  # --half FP16 inference arg
         s = "# WARNING ⚠️ ClassificationModel not yet supported for PyTorch Hub AutoShape inference" if cls else \
             "# WARNING ⚠️ SegmentationModel not yet supported for PyTorch Hub AutoShape inference" if seg else ''
         LOGGER.info(f'\nExport complete ({time.time() - t:.1f}s)'
                     f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
                     f"\nDetect:          yolov5 {'detect' if det else 'predict'} --weights {f[-1]} {h}"
-                    f"\nValidate:        yolov5 val --weights {f[-1]} {h}"
-                    f"\nPython:          model = yolov5.load('{f[-1]}')  {s}"
+                    f"\nValidate:        yolov5 yolov5 val --weights {f[-1]} {h}"
+                    f"\nnPython:         model = yolov5.load('{f[-1]}')  {s}"
                     f"\nVisualize:       https://netron.app")
     return f  # return list of exported files/dirs
 

diff --git a/yolov5/models/common.py b/yolov5/models/common.py
@@ -692,9 +692,9 @@ def forward(self, ims, size=640, augment=False, profile=False):
                 s = im.shape[:2]  # HWC
                 shape0.append(s)  # image shape
                 g = max(size) / max(s)  # gain
-                shape1.append([y * g for y in s])
+                shape1.append([int(y * g) for y in s])
                 ims[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
-            shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)] if self.pt else size  # inf shape
+            shape1 = [make_divisible(x, self.stride) for x in np.array(shape1).max(0)]  # inf shape
             x = [letterbox(im, shape1, auto=False)[0] for im in ims]  # pad
             x = np.ascontiguousarray(np.array(x).transpose((0, 3, 1, 2)))  # stack and BHWC to BCHW
             x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32

diff --git a/yolov5/models/tf.py b/yolov5/models/tf.py
@@ -333,6 +333,7 @@ def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), imgsz=(640, 640), w
 
     def call(self, x):
         p = self.proto(x[0])
+        # p = TFUpsample(None, scale_factor=4, mode='nearest')(self.proto(x[0]))  # (optional) full-size protos
         p = tf.transpose(p, [0, 3, 1, 2])  # from shape(1,160,160,32) to shape(1,32,160,160)
         x = self.detect(self, x)
         return (x, p) if self.training else (x[0], p)
@@ -355,8 +356,8 @@ class TFUpsample(keras.layers.Layer):
     # TF version of torch.nn.Upsample()
     def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
         super().__init__()
-        assert scale_factor == 2, "scale_factor must be 2"
-        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
+        assert scale_factor % 2 == 0, "scale_factor must be multiple of 2"
+        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * scale_factor, x.shape[2] * scale_factor), mode)
         # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
         # with default arguments: align_corners=False, half_pixel_centers=False
         # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
-Original file line number
+Diff line change
@@ Expand Up @@
     </div>
     <br>
-    This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/tree/8236d8818bca21c692d5c4508fee2af835ec1dbe">at this commit</a> plus:
+    This yolov5 package contains everything from ultralytics/yolov5 <a href="https://github.com/ultralytics/yolov5/commit/357cde9ee7da13ba3095995488c5a23631467f1a">at this commit</a> plus:
     <br>
 . Easy installation via pip: `pip install yolov5`
     <br>
@@ Expand Down @@