added lighter yolov5 config files

export.py

@@ -449,6 +449,7 @@ def transform_fn(data_item):
             Quantization transform function.
 
             Extracts and preprocess input data from dataloader item for quantization.
+
             Parameters:
                data_item: Tuple with data item produced by DataLoader during iteration
             Returns:

models/yolov5femto.yaml

@@ -0,0 +1,49 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.04 # model depth multiple
+width_multiple: 0.03125 # 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, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+  ]

models/yolov5micro.yaml

@@ -0,0 +1,49 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.16 # model depth multiple
+width_multiple: 0.125 # 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, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+  ]

models/yolov5pico.yaml

@@ -0,0 +1,49 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.08 # model depth multiple
+width_multiple: 0.0625 # 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, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+  ]

utils/augmentations.py

@@ -156,7 +156,6 @@ def random_perspective(
 ):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
     # targets = [cls, xyxy]
-
     """Applies random perspective transformation to an image, modifying the image and corresponding labels."""
     height = im.shape[0] + border[0] * 2  # shape(h,w,c)
     width = im.shape[1] + border[1] * 2

utils/callbacks.py

@@ -64,7 +64,6 @@ def run(self, hook, *args, thread=False, **kwargs):
             thread: (boolean) Run callbacks in daemon thread
             kwargs: Keyword Arguments to receive from YOLOv5
         """
-
         assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
         for logger in self._callbacks[hook]:
             if thread:

utils/dataloaders.py

@@ -1104,7 +1104,8 @@ def extract_boxes(path=DATASETS_DIR / "coco128"):
 def autosplit(path=DATASETS_DIR / "coco128/images", weights=(0.9, 0.1, 0.0), annotated_only=False):
     """Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
     Usage: from utils.dataloaders import *; autosplit()
-    Arguments
+
+    Arguments:
         path:            Path to images directory
         weights:         Train, val, test weights (list, tuple)
         annotated_only:  Only use images with an annotated txt file
@@ -1183,7 +1184,7 @@ class HUBDatasetStats:
     """
     Class for generating HUB dataset JSON and `-hub` dataset directory.
 
-    Arguments
+    Arguments:
         path:           Path to data.yaml or data.zip (with data.yaml inside data.zip)
         autodownload:   Attempt to download dataset if not found locally
 
@@ -1314,7 +1315,7 @@ class ClassificationDataset(torchvision.datasets.ImageFolder):
     """
     YOLOv5 Classification Dataset.
 
-    Arguments
+    Arguments:
         root:  Dataset path
         transform:  torchvision transforms, used by default
         album_transform: Albumentations transforms, used if installed

utils/general.py

@@ -518,7 +518,6 @@ def check_font(font=FONT, progress=False):
 
 def check_dataset(data, autodownload=True):
     """Validates and/or auto-downloads a dataset, returning its configuration as a dictionary."""
-
     # Download (optional)
     extract_dir = ""
     if isinstance(data, (str, Path)) and (is_zipfile(data) or is_tarfile(data)):
@@ -1023,7 +1022,6 @@ def non_max_suppression(
     Returns:
          list of detections, on (n,6) tensor per image [xyxy, conf, cls]
     """
-
     # Checks
     assert 0 <= conf_thres <= 1, f"Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0"
     assert 0 <= iou_thres <= 1, f"Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0"

utils/loggers/__init__.py

@@ -350,7 +350,8 @@ class GenericLogger:
     """
     YOLOv5 General purpose logger for non-task specific logging
     Usage: from utils.loggers import GenericLogger; logger = GenericLogger(...)
-    Arguments
+
+    Arguments:
         opt:             Run arguments
         console_logger:  Console logger
         include:         loggers to include

utils/loggers/clearml/clearml_utils.py

@@ -80,7 +80,7 @@ def __init__(self, opt, hyp):
         - Initialize ClearML Task, this object will capture the experiment
         - Upload dataset version to ClearML Data if opt.upload_dataset is True
 
-        arguments:
+        Arguments:
         opt (namespace) -- Commandline arguments for this run
         hyp (dict) -- Hyperparameters for this run
 
@@ -133,7 +133,7 @@ def log_scalars(self, metrics, epoch):
         """
         Log scalars/metrics to ClearML.
 
-        arguments:
+        Arguments:
         metrics (dict) Metrics in dict format: {"metrics/mAP": 0.8, ...}
         epoch (int) iteration number for the current set of metrics
         """
@@ -145,7 +145,7 @@ def log_model(self, model_path, model_name, epoch=0):
         """
         Log model weights to ClearML.
 
-        arguments:
+        Arguments:
         model_path (PosixPath or str) Path to the model weights
         model_name (str) Name of the model visible in ClearML
         epoch (int) Iteration / epoch of the model weights
@@ -158,7 +158,7 @@ def log_summary(self, metrics):
         """
         Log final metrics to a summary table.
 
-        arguments:
+        Arguments:
         metrics (dict) Metrics in dict format: {"metrics/mAP": 0.8, ...}
         """
         for k, v in metrics.items():
@@ -168,7 +168,7 @@ def log_plot(self, title, plot_path):
         """
         Log image as plot in the plot section of ClearML.
 
-        arguments:
+        Arguments:
         title (str) Title of the plot
         plot_path (PosixPath or str) Path to the saved image file
         """
@@ -183,7 +183,7 @@ def log_debug_samples(self, files, title="Debug Samples"):
         """
         Log files (images) as debug samples in the ClearML task.
 
-        arguments:
+        Arguments:
         files (List(PosixPath)) a list of file paths in PosixPath format
         title (str) A title that groups together images with the same values
         """
@@ -199,7 +199,7 @@ def log_image_with_boxes(self, image_path, boxes, class_names, image, conf_thres
         """
         Draw the bounding boxes on a single image and report the result as a ClearML debug sample.
 
-        arguments:
+        Arguments:
         image_path (PosixPath) the path the original image file
         boxes (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class]
         class_names (dict): dict containing mapping of class int to class name

utils/loggers/wandb/wandb_utils.py

@@ -49,7 +49,7 @@ def __init__(self, opt, run_id=None, job_type="Training"):
         - Upload dataset if opt.upload_dataset is True
         - Setup training processes if job_type is 'Training'
 
-        arguments:
+        Arguments:
         opt (namespace) -- Commandline arguments for this run
         run_id (str) -- Run ID of W&B run to be resumed
         job_type (str) -- To set the job_type for this run
@@ -90,7 +90,7 @@ def setup_training(self, opt):
           - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded
           - Setup log_dict, initialize bbox_interval
 
-        arguments:
+        Arguments:
         opt (namespace) -- commandline arguments for this run
 
         """
@@ -120,7 +120,7 @@ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
         """
         Log the model checkpoint as W&B artifact.
 
-        arguments:
+        Arguments:
         path (Path)   -- Path of directory containing the checkpoints
         opt (namespace) -- Command line arguments for this run
         epoch (int)  -- Current epoch number
@@ -159,7 +159,7 @@ def log(self, log_dict):
         """
         Save the metrics to the logging dictionary.
 
-        arguments:
+        Arguments:
         log_dict (Dict) -- metrics/media to be logged in current step
         """
         if self.wandb_run:
@@ -170,7 +170,7 @@ def end_epoch(self):
         """
         Commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
 
-        arguments:
+        Arguments:
         best_result (boolean): Boolean representing if the result of this evaluation is best or not
         """
         if self.wandb_run:
@@ -197,7 +197,7 @@ def finish_run(self):
 
 @contextmanager
 def all_logging_disabled(highest_level=logging.CRITICAL):
-    """source - https://gist.github.com/simon-weber/7853144
+    """Source - https://gist.github.com/simon-weber/7853144
     A context manager that will prevent any logging messages triggered during the body from being processed.
     :param highest_level: the maximum logging level in use.
       This would only need to be changed if a custom level greater than CRITICAL is defined.