Updates

rpi/training/utils/debug.py

@@ -0,0 +1,26 @@
+from pathlib import Path
+
+label_dir = Path("./datasets/your_dataset/val/labels")
+
+def valid_line(line):
+    parts = line.split()
+    if len(parts) != 5:
+        return False
+    cls, x, y, w, h = map(float, parts)
+    return 0 <= cls and 0 < w <= 1 and 0 < h <= 1
+
+
+empty = []
+for p in label_dir.glob("*.txt"):
+    if p.stat().st_size == 0:
+        empty.append(p.name)
+
+print(f"Empty label files: {len(empty)}")
+
+invalid = []
+for p in label_dir.glob("*.txt"):
+    lines = p.read_text().strip().splitlines()
+    if not any(valid_line(l) for l in lines):
+        invalid.append(p.name)
+
+print(f"Effectively empty labels: {len(invalid)}")

rpi/training/utils/decrease_labels.py

@@ -0,0 +1,36 @@
+import os
+
+# --------------------------
+# Configuration
+# --------------------------
+labels_dir = "datasets/visiope/test/labels"
+
+# --------------------------
+# Process each label file
+# --------------------------
+for filename in os.listdir(labels_dir):
+    if not filename.endswith(".txt"):
+        continue
+
+    txt_path = os.path.join(labels_dir, filename)
+    new_lines = []
+
+    with open(txt_path, "r") as f:
+        lines = f.readlines()
+
+    for line in lines:
+        parts = line.strip().split()
+        if len(parts) < 5:
+            continue  # skip invalid lines
+        cls = int(parts[0])
+        cls -= 1  # subtract 1 from class index
+        cls = max(cls, 0)  # ensure no negative indices
+        new_lines.append(" ".join([str(cls)] + parts[1:]))
+
+    # Overwrite file with updated indices
+    with open(txt_path, "w") as f:
+        f.write("\n".join(new_lines))
+
+    print(f"Updated {filename}")
+
+print("All label files have been adjusted!")

rpi/training/utils/remove_labels.py

@@ -0,0 +1,33 @@
+import os
+
+labels_dir = "../datasets/corners/Outer Chess Corners.v1i.yolov11/valid/labels"
+label_to_be_removed = 1
+
+for filename in os.listdir(labels_dir):
+    if not filename.endswith(".txt"):
+        continue
+
+    txt_path = os.path.join(labels_dir, filename)
+    new_lines = []
+
+    with open(txt_path, "r") as f:
+        lines = f.readlines()
+
+    for line in lines:
+        parts = line.strip().split()
+
+        if len(parts) < 5:
+            continue
+
+        cls = int(parts[0])
+        if cls == label_to_be_removed:
+            print(f"{parts} found in {filename}")
+            continue
+
+        new_lines.append(" ".join([str(cls)] + parts[1:]))
+
+    # Overwrite file with updated indices
+    with open(txt_path, "w") as f:
+        f.write("\n".join(new_lines))
+
+print("All label files have been adjusted!")

rpi/training/utils/remover.py

@@ -0,0 +1,16 @@
+import os
+
+# Paths to the folders
+folder_to_check = "./datasets/roboflow/train/labels"
+folder_with_files = "./datasets/unified/train/labels"
+
+files_to_check = set(os.listdir(folder_to_check))
+
+for filename in os.listdir(folder_with_files):
+    file_path = os.path.join(folder_with_files, filename)
+    if filename in files_to_check and os.path.isfile(file_path):
+        try:
+            os.remove(file_path)
+            print(f"Deleted: {file_path}")
+        except Exception as e:
+            print(f"Error deleting {file_path}: {e}")

rpi/training/utils/sort_labels.py

@@ -0,0 +1,71 @@
+import os
+import shutil
+
+
+def copy_images(src, dest):
+    image_extensions = [".jpg", ".jpeg", ".png", ".bmp", ".gif"]
+
+    for filename in os.listdir(src):
+        if any(filename.lower().endswith(ext) for ext in image_extensions):
+            src_path = os.path.join(src, filename)
+            dst_path = os.path.join(dest, filename)
+            shutil.copy2(src_path, dst_path)
+
+
+def remap_labels(src, dest):
+    count = 0
+    for filename in os.listdir(src):
+        if filename.endswith(".txt"):
+            input_path = os.path.join(src, filename)
+            output_path = os.path.join(dest, filename)
+
+            with open(input_path, "r") as f:
+                lines = f.readlines()
+
+            new_lines = []
+            for line in lines:
+                parts = line.strip().split()
+                old_idx = int(parts[0])
+                new_idx = index_map[old_idx]
+                new_lines.append(" ".join([str(new_idx)] + parts[1:]))
+
+            with open(output_path, "w") as f:
+                f.write("\n".join(new_lines))
+
+            if count%100 == 0:
+                print(count)
+            count += 1
+
+        print(f"All labels remapped and saved to '{dest}'")
+
+
+if __name__ == "__main__":
+
+    src_dir = "../datasets/pieces/visualizan/"
+    dest_dir = "../datasets/pieces/unified/"
+
+    reference_classes = [
+        'w_pawn', 'w_knight', 'w_bishop', 'w_rook', 'w_queen', 'w_king',
+        'b_pawn', 'b_knight', 'b_bishop', 'b_rook', 'b_queen', 'b_king'
+    ]
+
+    current_classes = ['b_bishop', 'b_king', 'b_knight', 'b_pawn', 'b_queen', 'b_rook',
+        'w_bishop', 'w_king', 'w_knight', 'w_pawn', 'w_queen', 'w_rook']
+
+    index_map = {current_classes.index(cls): reference_classes.index(cls) for cls in current_classes}
+
+    sub_elements = os.listdir(src_dir)
+    for sub in sub_elements:
+        src_full_path = os.path.normpath(os.path.join(src_dir, sub))
+        dest_full_path = os.path.normpath(os.path.join(dest_dir, sub))
+
+        if not os.path.isdir(src_full_path): continue
+
+        src_image_folder = os.path.normpath(os.path.join(src_full_path, "images"))
+        src_labels_folder = os.path.normpath(os.path.join(src_full_path, "labels"))
+
+        dst_image_folder = os.path.normpath(os.path.join(dest_full_path, "images"))
+        dst_labels_folder = os.path.normpath(os.path.join(dest_full_path, "labels"))
+
+        copy_images(src_image_folder, dst_image_folder)
+        remap_labels(src_labels_folder, dst_labels_folder)

rpi/training/utils/verifiy.py

@@ -0,0 +1,47 @@
+import os
+
+if __name__ == "__main__":
+    trg_dir = "../datasets/pieces/unified/train/labels"
+    src_dir = "../datasets/pieces/khalid/train/labels"
+
+    trg_labels = [
+        'w_pawn','w_knight','w_bishop','w_rook','w_queen','w_king',
+        'b_pawn','b_knight','b_bishop','b_rook','b_queen','b_king'
+    ]
+
+    src_labels = [
+        'b_bishop', 'b_king', 'b_knight', 'b_queen', 'b_rook', 'b_pawn',
+        'w_bishop', 'w_king', 'w_knight', 'w_queen', 'w_rook', 'w_pawn'
+    ]
+
+    trg_files = os.listdir(trg_dir)
+    src_files = os.listdir(src_dir)
+
+    for src_file in src_files:
+        trg_file = os.path.abspath(os.path.join(trg_dir, src_file))
+        src_file = os.path.abspath(os.path.join(src_dir, src_file))
+
+        trg_lines = []
+        src_lines = []
+
+        with open(src_file, "r") as f:
+            src_lines = f.readlines().copy()
+
+        with open(trg_file, "r") as f:
+            trg_lines = f.readlines().copy()
+
+        for i in range(0, len(trg_lines)):
+            trg_line = trg_lines[i]
+            src_line  = src_lines[i]
+
+            trg_label_index = int(trg_line.strip().split(" ")[0])
+            src_label_index = int(src_line.strip().split(" ")[0])
+
+            trg_label_value = trg_labels[trg_label_index]
+            src_label_value = src_labels[src_label_index]
+
+            if trg_label_value != src_label_value :
+                print(f"Error detected in {trg_file} at line {i}.\n"
+                      f"==> Index {trg_label_index} points to {trg_label_value} instead of {src_label_index}:{src_label_value}")
+
+print("Detection terminated.")