Small fix

src/gui/tabs/training_tab.py

@@ -34,7 +34,7 @@ from PySide6.QtWidgets import (
 from src.database.db_manager import DatabaseManager
 from src.model.yolo_wrapper import YOLOWrapper
 from src.utils.config_manager import ConfigManager
-from src.utils.image import Image, convert_grayscale_to_rgb_preserve_range
+from src.utils.image import Image
 from src.utils.logger import get_logger
 
 
@@ -1368,7 +1368,7 @@ class TrainingTab(QWidget):
                 img_obj = Image(src)
                 pil_img = img_obj.pil_image
                 if len(pil_img.getbands()) == 1:
-                    rgb_img = convert_grayscale_to_rgb_preserve_range(pil_img)
+                    rgb_img = img_obj.convert_grayscale_to_rgb_preserve_range()
                 else:
                     rgb_img = pil_img.convert("RGB")
                 rgb_img.save(dst)

src/model/yolo_wrapper.py

@@ -9,7 +9,7 @@ from typing import Optional, List, Dict, Callable, Any
 import torch
 import tempfile
 import os
-from src.utils.image import Image, convert_grayscale_to_rgb_preserve_range
+from src.utils.image import Image
 from src.utils.logger import get_logger
 
 
@@ -238,7 +238,7 @@ class YOLOWrapper:
                     img_obj = Image(source_path)
                     pil_img = img_obj.pil_image
                     if len(pil_img.getbands()) == 1:
-                        rgb_img = convert_grayscale_to_rgb_preserve_range(pil_img)
+                        rgb_img = img_obj.convert_grayscale_to_rgb_preserve_range()
                     else:
                         rgb_img = pil_img.convert("RGB")
 

src/utils/image.py

@@ -277,6 +277,38 @@ class Image:
         """
         return self._channels >= 3
 
+    def convert_grayscale_to_rgb_preserve_range(
+        self,
+    ) -> PILImage.Image:
+        """Convert a single-channel PIL image to RGB while preserving dynamic range.
+
+        Returns:
+            PIL Image in RGB mode with intensities normalized to 0-255.
+        """
+        if self._channels == 3:
+            return self.pil_image
+
+        grayscale = self.data
+        if grayscale.ndim == 3:
+            grayscale = grayscale[:, :, 0]
+
+        original_dtype = grayscale.dtype
+        grayscale = grayscale.astype(np.float32)
+
+        if grayscale.size == 0:
+            return PILImage.new("RGB", self.shape, color=(0, 0, 0))
+
+        if np.issubdtype(original_dtype, np.integer):
+            denom = float(max(np.iinfo(original_dtype).max, 1))
+        else:
+            max_val = float(grayscale.max())
+            denom = max(max_val, 1.0)
+
+        grayscale = np.clip(grayscale / denom, 0.0, 1.0)
+        grayscale_u8 = (grayscale * 255.0).round().astype(np.uint8)
+        rgb_arr = np.repeat(grayscale_u8[:, :, None], 3, axis=2)
+        return PILImage.fromarray(rgb_arr, mode="RGB")
+
     def __repr__(self) -> str:
         """String representation of the Image object."""
         return (
@@ -289,40 +321,3 @@ class Image:
     def __str__(self) -> str:
         """String representation of the Image object."""
         return self.__repr__()
-
-
-def convert_grayscale_to_rgb_preserve_range(
-    pil_image: PILImage.Image,
-) -> PILImage.Image:
-    """Convert a single-channel PIL image to RGB while preserving dynamic range.
-
-    Args:
-        pil_image: Single-channel PIL image (e.g., 16-bit grayscale).
-
-    Returns:
-        PIL Image in RGB mode with intensities normalized to 0-255.
-    """
-
-    if pil_image.mode == "RGB":
-        return pil_image
-
-    grayscale = np.array(pil_image)
-    if grayscale.ndim == 3:
-        grayscale = grayscale[:, :, 0]
-
-    original_dtype = grayscale.dtype
-    grayscale = grayscale.astype(np.float32)
-
-    if grayscale.size == 0:
-        return PILImage.new("RGB", pil_image.size, color=(0, 0, 0))
-
-    if np.issubdtype(original_dtype, np.integer):
-        denom = float(max(np.iinfo(original_dtype).max, 1))
-    else:
-        max_val = float(grayscale.max())
-        denom = max(max_val, 1.0)
-
-    grayscale = np.clip(grayscale / denom, 0.0, 1.0)
-    grayscale_u8 = (grayscale * 255.0).round().astype(np.uint8)
-    rgb_arr = np.repeat(grayscale_u8[:, :, None], 3, axis=2)
-    return PILImage.fromarray(rgb_arr, mode="RGB")

src/utils/image_converters.py

@@ -12,23 +12,32 @@ class UT:
     Operetta files along with rois drawn in ImageJ
     """
 
-    def __init__(self, roifile_fn: Path):
+    def __init__(self, roifile_fn: Path, no_labels: bool):
         self.roifile_fn = roifile_fn
+        print("is file", self.roifile_fn.is_file())
+        self.rois = None
+        if no_labels:
             self.rois = ImagejRoi.fromfile(self.roifile_fn)
-        self.stem = self.roifile_fn.stem.strip("-RoiSet")
+            self.stem = self.roifile_fn.stem.split("Roi-")[1]
+        else:
+            self.roifile_fn = roifile_fn / roifile_fn.parts[-1]
+            self.stem = self.roifile_fn.stem
+
+            print(self.roifile_fn)
+
+        print(self.stem)
         self.image, self.image_props = self._load_images()
 
     def _load_images(self):
         """Loading sequence of tif files
         array sequence is CZYX
         """
-        print(self.roifile_fn.parent, self.stem)
-        fns = list(self.roifile_fn.parent.glob(f"{self.stem}*.tif*"))
+        print("Loading images:", self.roifile_fn.parent, self.stem)
+        fns = list(self.roifile_fn.parent.glob(f"{self.stem.lower()}*.tif*"))
         stems = [fn.stem.split(self.stem)[-1] for fn in fns]
         n_ch = len(set([stem.split("-ch")[-1].split("t")[0] for stem in stems]))
         n_p = len(set([stem.split("-")[0] for stem in stems]))
         n_t = len(set([stem.split("t")[1] for stem in stems]))
-        print(n_ch, n_p, n_t)
 
         with TiffFile(fns[0]) as tif:
             img = tif.asarray()
@@ -42,6 +51,7 @@ class UT:
                 "height": h,
                 "dtype": dtype,
             }
+        print("Image props", self.image_props)
 
         image_stack = np.zeros((n_ch, n_p, w, h), dtype=dtype)
         for fn in fns:
@@ -49,7 +59,7 @@ class UT:
                 img = tif.asarray()
                 stem = fn.stem.split(self.stem)[-1]
                 ch = int(stem.split("-ch")[-1].split("t")[0])
-                p = int(stem.split("-")[0].lstrip("p"))
+                p = int(stem.split("-")[0].split("p")[1])
                 t = int(stem.split("t")[1])
                 print(fn.stem, "ch", ch, "p", p, "t", t)
                 image_stack[ch - 1, p - 1] = img
@@ -82,10 +92,21 @@ class UT:
     ):
         """Export rois to a file"""
         with open(path / subfolder / f"{self.stem}.txt", "w") as f:
-            for roi in self.rois:
-                # TODO add image coordinates normalization
-                coords = ""
-                for x, y in roi.subpixel_coordinates:
+            for i, roi in enumerate(self.rois):
+                rc = roi.subpixel_coordinates
+                if rc is None:
+                    print(
+                        f"No coordinates: {self.roifile_fn}, element {i}, out of {len(self.rois)}"
+                    )
+                    continue
+                xmn, ymn = rc.min(axis=0)
+                xmx, ymx = rc.max(axis=0)
+                xc = (xmn + xmx) / 2
+                yc = (ymn + ymx) / 2
+                bw = xmx - xmn
+                bh = ymx - ymn
+                coords = f"{xc/self.width} {yc/self.height} {bw/self.width} {bh/self.height} "
+                for x, y in rc:
                     coords += f"{x/self.width} {y/self.height} "
                 f.write(f"{class_index} {coords}\n")
 
@@ -104,6 +125,7 @@ class UT:
             self.image = np.max(self.image[channel], axis=0)
             print(self.image.shape)
 
+        print(path / subfolder / f"{self.stem}.tif")
         with TiffWriter(path / subfolder / f"{self.stem}.tif") as tif:
             tif.write(self.image)
 
@@ -112,11 +134,27 @@ if __name__ == "__main__":
     import argparse
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("input", type=Path)
-    parser.add_argument("output", type=Path)
+    parser.add_argument("-i", "--input", nargs="*", type=Path)
+    parser.add_argument("-o", "--output", type=Path)
+    parser.add_argument(
+        "--no-labels",
+        action="store_false",
+        help="Source does not have labels, export only images",
+    )
     args = parser.parse_args()
 
-    for rfn in args.input.glob("*.zip"):
-        ut = UT(rfn)
+    for path in args.input:
+        print("Path:", path)
+        if not args.no_labels:
+            print("No labels")
+            ut = UT(path, args.no_labels)
+            ut.export_image(args.output, plane_mode="max projection", channel=0)
+
+        else:
+            for rfn in Path(path).glob("*.zip"):
+                print("Roi FN:", rfn)
+                ut = UT(rfn, args.no_labels)
                 ut.export_rois(args.output, class_index=0)
                 ut.export_image(args.output, plane_mode="max projection", channel=0)
+
+        print()

tests/show_yolo_seg.py

@@ -0,0 +1,184 @@
+#!/usr/bin/env python3
+"""
+show_yolo_seg.py
+
+Usage:
+    python show_yolo_seg.py /path/to/image.jpg /path/to/labels.txt
+
+Supports:
+ - Segmentation polygons: "class x1 y1 x2 y2 ... xn yn"
+ - YOLO bbox lines as fallback: "class x_center y_center width height"
+Coordinates can be normalized [0..1] or absolute pixels (auto-detected).
+"""
+import sys
+import cv2
+import numpy as np
+import matplotlib.pyplot as plt
+import argparse
+from pathlib import Path
+import random
+
+
+def parse_label_line(line):
+    parts = line.strip().split()
+    if not parts:
+        return None
+    cls = int(float(parts[0]))
+    coords = [float(x) for x in parts[1:]]
+    return cls, coords
+
+
+def coords_are_normalized(coords):
+    # If every coordinate is between 0 and 1 (inclusive-ish), assume normalized
+    if not coords:
+        return False
+    return max(coords) <= 1.001
+
+
+def yolo_bbox_to_xyxy(coords, img_w, img_h):
+    # coords: [xc, yc, w, h] normalized or absolute
+    xc, yc, w, h = coords[:4]
+    if max(coords) <= 1.001:
+        xc *= img_w
+        yc *= img_h
+        w *= img_w
+        h *= img_h
+    x1 = int(round(xc - w / 2))
+    y1 = int(round(yc - h / 2))
+    x2 = int(round(xc + w / 2))
+    y2 = int(round(yc + h / 2))
+    return x1, y1, x2, y2
+
+
+def poly_to_pts(coords, img_w, img_h):
+    # coords: [x1 y1 x2 y2 ...] either normalized or absolute
+    if coords_are_normalized(coords[4:]):
+        coords = [
+            coords[i] * (img_w if i % 2 == 0 else img_h) for i in range(len(coords))
+        ]
+    pts = np.array(coords, dtype=np.int32).reshape(-1, 2)
+    return pts
+
+
+def random_color_for_class(cls):
+    random.seed(cls)  # deterministic per class
+    return tuple(int(x) for x in np.array([random.randint(0, 255) for _ in range(3)]))
+
+
+def draw_annotations(img, labels, alpha=0.4, draw_bbox_for_poly=True):
+    # img: BGR numpy array
+    overlay = img.copy()
+    h, w = img.shape[:2]
+    for cls, coords in labels:
+        if not coords:
+            continue
+        # polygon case (>=6 coordinates)
+        if len(coords) >= 6:
+            color = random_color_for_class(cls)
+
+            x1, y1, x2, y2 = yolo_bbox_to_xyxy(coords[:4], w, h)
+            cv2.rectangle(img, (x1, y1), (x2, y2), color, 2)
+
+            pts = poly_to_pts(coords[4:], w, h)
+            # fill on overlay
+            cv2.fillPoly(overlay, [pts], color)
+            # outline on base image
+            cv2.polylines(img, [pts], isClosed=True, color=color, thickness=2)
+            # put class text at first point
+            x, y = int(pts[0, 0]), int(pts[0, 1]) - 6
+            cv2.putText(
+                img,
+                str(cls),
+                (x, max(6, y)),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                0.6,
+                (255, 255, 255),
+                2,
+                cv2.LINE_AA,
+            )
+
+        # YOLO bbox case (4 coords)
+        elif len(coords) == 4:
+            x1, y1, x2, y2 = yolo_bbox_to_xyxy(coords, w, h)
+            color = random_color_for_class(cls)
+            cv2.rectangle(img, (x1, y1), (x2, y2), color, 2)
+            cv2.putText(
+                img,
+                str(cls),
+                (x1, max(6, y1 - 4)),
+                cv2.FONT_HERSHEY_SIMPLEX,
+                0.6,
+                (255, 255, 255),
+                2,
+                cv2.LINE_AA,
+            )
+        else:
+            # Unknown / invalid format, skip
+            continue
+
+    # blend overlay for filled polygons
+    cv2.addWeighted(overlay, alpha, img, 1 - alpha, 0, img)
+    return img
+
+
+def load_labels_file(label_path):
+    labels = []
+    with open(label_path, "r") as f:
+        for raw in f:
+            line = raw.strip()
+            if not line:
+                continue
+            parsed = parse_label_line(line)
+            if parsed:
+                labels.append(parsed)
+    return labels
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Show YOLO segmentation / polygon annotations"
+    )
+    parser.add_argument("image", type=str, help="Path to image file")
+    parser.add_argument("labels", type=str, help="Path to YOLO label file (polygons)")
+    parser.add_argument(
+        "--alpha", type=float, default=0.4, help="Polygon fill alpha (0..1)"
+    )
+    parser.add_argument(
+        "--no-bbox", action="store_true", help="Don't draw bounding boxes for polygons"
+    )
+    args = parser.parse_args()
+
+    img_path = Path(args.image)
+    lbl_path = Path(args.labels)
+
+    if not img_path.exists():
+        print("Image not found:", img_path)
+        sys.exit(1)
+    if not lbl_path.exists():
+        print("Label file not found:", lbl_path)
+        sys.exit(1)
+
+    img = cv2.imread(str(img_path), cv2.IMREAD_COLOR)
+    if img is None:
+        print("Could not load image:", img_path)
+        sys.exit(1)
+
+    labels = load_labels_file(str(lbl_path))
+    if not labels:
+        print("No labels parsed from", lbl_path)
+        # continue and just show image
+    out = draw_annotations(
+        img.copy(), labels, alpha=args.alpha, draw_bbox_for_poly=(not args.no_bbox)
+    )
+
+    # Convert BGR -> RGB for matplotlib display
+    out_rgb = cv2.cvtColor(out, cv2.COLOR_BGR2RGB)
+    plt.figure(figsize=(10, 10 * out.shape[0] / out.shape[1]))
+    plt.imshow(out_rgb)
+    plt.axis("off")
+    plt.title(f"{img_path.name} ({lbl_path.name})")
+    plt.show()
+
+
+if __name__ == "__main__":
+    main()