🔨 [Init] the base train code, and load yaml cfg

config/model/v7-base.yaml

@@ -0,0 +1,239 @@
+anchor:
+  [1, 2, 3]
+model:
+  backbone:
+  - Conv: 
+      args: {out_channels: 32, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3, stride: 2}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3, stride: 2}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Concat: 
+      source: [-1, -3, -5, -6]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - MP: 
+      args: []
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+      source: -3
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3, stride: 2}
+  - Concat: 
+      source: [-1, -3]
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Concat: 
+      source: [-1, -3, -5, -6]
+      tags: 8x
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+  - MP: 
+      args: []
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -3
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3, stride: 2}
+  - Concat: 
+      source: [-1, -3]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Concat: 
+      source: [-1, -3, -5, -6]
+  - Conv: 
+      args: {out_channels: 1024, kernel_size: 1}
+      tags: 16x
+  - MP: 
+      args: []
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+      source: -3
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 3, stride: 2}
+  - Concat: 
+      source: [-1, -3]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Concat: 
+      source: [-1, -3, -5, -6]
+  - Conv: 
+      args: {out_channels: 1024, kernel_size: 1}
+      tags: 32x
+  head:
+  - SPPCSPC: 
+      args: [512]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Upsample: 
+      args: [None, 2, nearest]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: 16x
+  - Concat: 
+      source: [-1, -2]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Concat: 
+      source: [-1, -2, -3, -4, -5, -6]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - Upsample: 
+      args: [None, 2, nearest]
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+      source: 8x
+  - Concat: 
+      source: [-1, -2]
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 64, kernel_size: 3}
+  - Concat: 
+      source: [-1, -2, -3, -4, -5, -6]
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - MP: 
+      args: []
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 1}
+      source: -3
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3, stride: 2}
+  - Concat: 
+      source: [-1, -3, 63]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 128, kernel_size: 3}
+  - Concat: 
+      source: [-1, -2, -3, -4, -5, -6]
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - MP: 
+      args: []
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 1}
+      source: -3
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3, stride: 2}
+  - Concat: 
+      source: [-1, -3, 51]
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+      source: -2
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Conv: 
+      args: {out_channels: 256, kernel_size: 3}
+  - Concat: 
+      source: [-1, -2, -3, -4, -5, -6]
+  - Conv: 
+      args: {out_channels: 512, kernel_size: 1}
+  - RepConv: 
+      args: [256, 3, 1]
+      source: 75
+  - RepConv: 
+      args: [512, 3, 1]
+      source: 88
+  - RepConv: 
+      args: [1024, 3, 1]
+      source: 101
+  - IDetect: 
+      args: [nc, anchors]
+      source: [102, 103, 104]

model/yolo.py

@@ -0,0 +1,35 @@
+import torch.nn as nn
+from loguru import logger
+from typing import Dict, Any
+
+
+class YOLO(nn.Module):
+    """
+    A preliminary YOLO (You Only Look Once) model class still under development.
+
+    This class is intended to define a YOLO model for object detection tasks. It is
+    currently not implemented and serves as a placeholder for future development.
+
+    Parameters:
+        model_cfg: Configuration for the YOLO model. Expected to define the layers,
+                   parameters, and any other relevant configuration details.
+    """
+
+    def __init__(self, model_cfg: Dict[str, Any]):
+        super(YOLO, self).__init__()
+        # Placeholder for initialization logic
+        print(model_cfg)
+        raise NotImplementedError("Constructor not implemented.")
+
+
+def get_model(model_cfg: dict) -> YOLO:
+    """Constructs and returns a model from a Dictionary configuration file.
+
+    Args:
+        config_file (dict): The configuration file of the model.
+
+    Returns:
+        YOLO: An instance of the model defined by the given configuration.
+    """
+    model = YOLO(model_cfg)
+    return model

train.py

@@ -0,0 +1,26 @@
+import argparse
+import sys
+from loguru import logger
+from model.yolo import get_model
+from utils.tools import load_model_cfg
+
+
+def parse_arguments() -> argparse.Namespace:
+    """
+    Parse command-line arguments to get the model configuration file.
+
+    Returns:
+        argparse.Namespace: The command-line arguments object with 'config' attribute.
+    """
+    parser = argparse.ArgumentParser(description="Load a YOLO model configuration and display the model.")
+    parser.add_argument(
+        "--model-config", type=str, default="v7-base.yaml", help="Name or path to the model configuration file."
+    )
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    args = parse_arguments()
+    model_cfg = load_model_cfg(args.model_config)
+    model = get_model(model_cfg)
+    logger.info("Success load model: {}", model)

utils/tools.py

@@ -0,0 +1,67 @@
+import os
+import yaml
+from loguru import logger
+from typing import Dict, Any
+
+
+def complete_path(file_name: str = "v7-base.yaml") -> str:
+    """
+    Ensures the path to a model configuration is a existing file
+
+    Parameters:
+        file_name (str): The filename or path, with default 'v7-base.yaml'.
+
+    Returns:
+        str: A complete path with necessary prefix and extension.
+    """
+    # Ensure the file has the '.yaml' extension if missing
+    if not file_name.endswith(".yaml"):
+        file_name += ".yaml"
+
+    # Add folder prefix if only the filename is provided
+    if os.path.dirname(file_name) == "":
+        file_name = os.path.join("./config/model", file_name)
+
+    return file_name
+
+
+def load_model_cfg(file_path: str) -> Dict[str, Any]:
+    """
+    Read a YAML configuration file, ensure necessary keys are present, and return its content as a dictionary.
+
+    Args:
+        file_path (str): The path to the YAML configuration file.
+
+    Returns:
+        Dict[str, Any]: The contents of the YAML file as a dictionary.
+
+    Raises:
+        FileNotFoundError: If the YAML file cannot be found.
+        yaml.YAMLError: If there is an error parsing the YAML file.
+    """
+    file_path = complete_path(file_path)
+    try:
+        with open(file_path, "r") as file:
+            model_cfg = yaml.safe_load(file) or {}
+
+        # Check for required keys and set defaults if not present
+        if "nc" not in model_cfg:
+            model_cfg["nc"] = 80
+            logger.warning("'nc' not found in the YAML file. Setting default 'nc' to 80.")
+
+        if "anchor" not in model_cfg:
+            logger.error("'anchor' is missing in the configuration file.")
+            raise ValueError("Missing required key: 'anchor'")
+
+        if "model" not in model_cfg:
+            logger.error("'model' is missing in the configuration file.")
+            raise ValueError("Missing required key: 'model'")
+
+        return model_cfg
+
+    except FileNotFoundError:
+        logger.error(f"YAML file not found: {file_path}")
+        raise
+    except yaml.YAMLError as e:
+        logger.error(f"Error parsing YAML file: {e}")
+        raise