cli to control zed camera start and stop. 2. measure now use every svo2 file for 1 fish, give intermideate result and final result with confidecne level(*).

FishMeasure/fish_video_weight_evaluation.py

@@ -10,6 +10,24 @@ import json
 import numpy as np
 import torch
 from pathlib import Path
+
+if not hasattr(argparse, "BooleanOptionalAction"):
+    class _BooleanOptionalAction(argparse.Action):
+        def __init__(self, option_strings, dest, default=None, type=None,
+                     choices=None, required=False, help=None, metavar=None):
+            _option_strings = []
+            for opt in option_strings:
+                _option_strings.append(opt)
+                if opt.startswith("--"):
+                    _option_strings.append("--no-" + opt[2:])
+            super().__init__(option_strings=_option_strings, dest=dest, nargs=0,
+                             default=default, type=type, choices=choices,
+                             required=required, help=help, metavar=metavar)
+
+        def __call__(self, parser, namespace, values, option_string=None):
+            setattr(namespace, self.dest, not option_string.startswith("--no-"))
+
+    argparse.BooleanOptionalAction = _BooleanOptionalAction
 from typing import List, Dict, Any, Optional, Tuple
 from ultralytics import YOLO
 from seg import init_models
@@ -20,6 +38,8 @@ import importlib
 import tempfile
 import subprocess
 
+_REPO_ROOT = Path(__file__).resolve().parent
+
 try:
     import pyzed.sl as sl
     ZED_AVAILABLE = True
@@ -936,7 +956,7 @@ def classify_pointcloud_array(classifier: torch.nn.Module, points: np.ndarray, c
         possible_paths = [
             Path(__file__).parent / "pointcloud_classifier" / "Pointnet_Pointnet2_pytorch" / "test_classification.py",
             Path(__file__).parent.parent / "pointcloud_classifier" / "Pointnet_Pointnet2_pytorch" / "test_classification.py",
-            Path("/home/ubuntu/projects/FishMeasure/pointcloud_classifier/Pointnet_Pointnet2_pytorch/test_classification.py"),
+            _REPO_ROOT / "pointcloud_classifier" / "Pointnet_Pointnet2_pytorch" / "test_classification.py",
         ]
         
         test_classification_path = None
@@ -2132,7 +2152,7 @@ def main():
         help="With --batch-svo-folder: find *.svo2 in all subfolders (output dirs use path like parent__child__file)",
     )
     parser.add_argument("--yolo-model", 
-                       default="/home/ubuntu/projects/FishMeasure/runs/train/fish_detection_20251127_104658/weights/best.pt",
+                       default=str(_REPO_ROOT / "runs/train/fish_detection_20251127_104658/weights/best.pt"),
                        help="YOLO model path")
     parser.add_argument("--conf", type=float, default=0.25, help="Confidence threshold")
     parser.add_argument("--imgsz", type=int, default=640, help="Image size")
@@ -2176,7 +2196,7 @@ def main():
     parser.add_argument("--run-weight-estimation", action="store_true",
                        help="After processing, run DGCNN weight estimation on saved point clouds (test_dgcnn_weight_estimator)")
     parser.add_argument("--weight-estimator-checkpoint", type=str, 
-                       default="/home/ubuntu/projects/FishMeasure/weight_estimator/runs/dgcnn_20260312_171043/best.pt",
+                       default=str(_REPO_ROOT / "weight_estimator/runs/dgcnn_20260312_171043/best.pt"),
                        help="Path to DGCNN weight estimator checkpoint (.pt)")
     parser.add_argument("--weight-topk-length", type=int, default=3,
                        help="Optional: length-weighted top-K for predict_cloud_folder (default: 3; set 0 to disable)")

FishMeasure/generate_video_with_labels.py

@@ -167,22 +167,41 @@ def generate_video(
     imgsz: int = 640,
     frame_stride: int = 1,
     show_large: bool = False,
+    summary_weight_g: Optional[float] = None,
+    summary_length_mm: Optional[float] = None,
+    summary_star: bool = False,
+    output_video_name: Optional[str] = None,
+    sam_device: str = "cuda",
 ) -> Optional[Path]:
     if not ZED_AVAILABLE:
         print("ERROR: pyzed not available, cannot generate labeled video")
         return None
 
-    per_frame, summary_wg, summary_lmm, is_confident = _parse_weight_json(weight_json)
-    star_s = " *" if is_confident else ""
+    per_frame, parsed_summary_wg, parsed_summary_lmm, raw_confident = _parse_weight_json(weight_json)
+    if summary_weight_g is None:
+        summary_weight_g = parsed_summary_wg
+    if summary_length_mm is None:
+        summary_length_mm = parsed_summary_lmm
+    star_s = " *" if summary_star else ""
     print(f"  Per-frame predictions: {len(per_frame)} PLYs mapped")
-    print(f"  Summary: weight={summary_wg}g, length={summary_lmm}mm{star_s}")
+    print(
+        f"  Summary: weight={summary_weight_g}g, length={summary_length_mm}mm{star_s} "
+        f"(raw_confident={raw_confident})"
+    )
 
-    if not per_frame and summary_wg is None:
+    if not per_frame and summary_weight_g is None:
         print("  WARNING: No weight data in JSON, video will show '--'")
 
     from ultralytics import YOLO
     yolo = YOLO(yolo_model_path)
     class_names = yolo.names if hasattr(yolo, "names") else {}
+    from fish_video_weight_evaluation import (
+        create_segmentation_overlay,
+        load_sam_predictor_with_fallback,
+        segment_with_sam,
+    )
+    sam_predictor, eff_sam_device = load_sam_predictor_with_fallback(sam_device)
+    sam_torch_device = eff_sam_device
 
     from dataset.zed_reader import ZEDReader
     zed_reader = ZEDReader(svo_path=str(svo_path), camera_mode=False, use_yolo_detector=False)
@@ -218,6 +237,7 @@ def generate_video(
                 continue
 
             frame_number = idx + 1
+            frame_name = f"frame_{frame_number:06d}"
             if frame_number in per_frame:
                 cur_wg, cur_lmm = per_frame[frame_number]
                 last_wg = cur_wg
@@ -230,6 +250,7 @@ def generate_video(
             num_dets = len(results.boxes) if results.boxes is not None else 0
 
             left_disp = img.copy()
+            right_disp = img.copy()
             if num_dets > 0:
                 boxes = results.boxes.xyxy.cpu().numpy()
                 tids = (results.boxes.id.cpu().numpy().astype(int)
@@ -245,19 +266,31 @@ def generate_video(
                     cname = class_names.get(cid, "fish")
                     _draw_label_on_box(left_disp, box, tid, cname, cur_wg, cur_lmm)
 
-            if show_large or summary_wg is not None:
-                _draw_large_summary(left_disp, summary_wg, summary_lmm, is_confident)
+                try:
+                    masks = segment_with_sam(sam_predictor, img, boxes, sam_torch_device)
+                except Exception as e:
+                    print(f"  WARNING: SAM segmentation failed on {frame_name}: {e}")
+                    masks = []
+
+                if masks:
+                    right_disp = create_segmentation_overlay(img.copy(), masks)
+                    cv2.putText(right_disp, "Segmentation", (10, right_disp.shape[0] - 20),
+                                cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2, cv2.LINE_AA)
+                else:
+                    cv2.putText(right_disp, "Segmentation (failed)", (10, right_disp.shape[0] - 20),
+                                cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 255), 2, cv2.LINE_AA)
+            else:
+                cv2.putText(right_disp, "No detections", (10, right_disp.shape[0] - 20),
+                            cv2.FONT_HERSHEY_SIMPLEX, 0.7, (128, 128, 128), 2, cv2.LINE_AA)
+
+            if show_large or summary_weight_g is not None:
+                _draw_large_summary(left_disp, summary_weight_g, summary_length_mm, summary_star)
 
-            frame_name = f"frame_{frame_number:06d}"
             info = f"[{frame_number}] {frame_name} | Detections: {num_dets}"
             cv2.putText(left_disp, info, (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0), 2, cv2.LINE_AA)
             cv2.putText(left_disp, "Detection", (10, left_disp.shape[0] - 20),
                         cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2, cv2.LINE_AA)
 
-            right_disp = img.copy()
-            cv2.putText(right_disp, "Original", (10, right_disp.shape[0] - 20),
-                        cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255, 255, 255), 2, cv2.LINE_AA)
-
             combined = np.hstack([left_disp, right_disp])
             if num_dets > 0:
                 frames.append(combined)
@@ -275,7 +308,7 @@ def generate_video(
         print(f"  WARNING: No detection frames collected from {svo_name}")
         return None
 
-    video_path = images_dir / f"{svo_name}_preview.mp4"
+    video_path = images_dir / (output_video_name or f"{svo_name}_preview.mp4")
     h, w = frames[0].shape[:2]
     writer = cv2.VideoWriter(str(video_path), cv2.VideoWriter_fourcc(*"mp4v"), 10.0, (w, h))
     for f in frames:
@@ -295,7 +328,17 @@ def main():
     parser.add_argument("--conf", type=float, default=0.25)
     parser.add_argument("--imgsz", type=int, default=640)
     parser.add_argument("--frame-stride", type=int, default=1)
+    parser.add_argument("--sam-device", type=str, default="cuda")
     parser.add_argument("--show-large-labels-at-top-right", action="store_true")
+    parser.add_argument(
+        "--summary-star",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Whether to draw * on the Final summary line; caller/DB is the source of truth.",
+    )
+    parser.add_argument("--summary-weight-g", type=float, default=None)
+    parser.add_argument("--summary-length-mm", type=float, default=None)
+    parser.add_argument("--output-video-name", type=str, default=None)
     args = parser.parse_args()
 
     svo = Path(args.svo).expanduser().resolve()
@@ -315,7 +358,12 @@ def main():
         conf=args.conf,
         imgsz=args.imgsz,
         frame_stride=args.frame_stride,
+        sam_device=args.sam_device,
         show_large=args.show_large_labels_at_top_right,
+        summary_weight_g=args.summary_weight_g,
+        summary_length_mm=args.summary_length_mm,
+        summary_star=bool(args.summary_star),
+        output_video_name=args.output_video_name,
     )
 
 

FishMeasure/predict_weigth_from_svo2.py

@@ -25,6 +25,24 @@ import subprocess
 import sys
 import math
 from pathlib import Path
+
+if not hasattr(argparse, "BooleanOptionalAction"):
+    class _BooleanOptionalAction(argparse.Action):
+        def __init__(self, option_strings, dest, default=None, type=None,
+                     choices=None, required=False, help=None, metavar=None):
+            _option_strings = []
+            for opt in option_strings:
+                _option_strings.append(opt)
+                if opt.startswith("--"):
+                    _option_strings.append("--no-" + opt[2:])
+            super().__init__(option_strings=_option_strings, dest=dest, nargs=0,
+                             default=default, type=type, choices=choices,
+                             required=required, help=help, metavar=metavar)
+
+        def __call__(self, parser, namespace, values, option_string=None):
+            setattr(namespace, self.dest, not option_string.startswith("--no-"))
+
+    argparse.BooleanOptionalAction = _BooleanOptionalAction
 from typing import Any, Dict, List, Optional, Tuple
 
 import torch
@@ -136,11 +154,14 @@ def _run_generate_video_with_labels_subprocess(
         "--conf", str(args.conf),
         "--imgsz", str(args.imgsz),
         "--frame-stride", str(args.frame_stride),
+        "--sam-device", str(args.sam_device),
         "--weight-json", str(weight_json.expanduser().resolve()),
     ]
 
     if getattr(args, "show_large_labels_at_top_right", False):
         cmd.append("--show-large-labels-at-top-right")
+    if getattr(args, "summary_star", False):
+        cmd.append("--summary-star")
 
     print(f"Invoking generate_video_with_labels.py:\n  {' '.join(cmd)}")
     proc = subprocess.run(cmd, cwd=str(REPO_ROOT))
@@ -505,7 +526,7 @@ def main() -> None:
     parser.add_argument(
         "--yolo-model",
         type=str,
-        default="/home/ubuntu/projects/FishMeasure/runs/train/fish_detection_20251127_104658/weights/best.pt",
+        default=str(REPO_ROOT / "runs/train/fish_detection_20251127_104658/weights/best.pt"),
     )
     parser.add_argument(
         "--conf",
@@ -622,6 +643,12 @@ def main() -> None:
         action="store_true",
         help="Show large weight/length labels (10x font) at top right corner for real/camera generated videos.",
     )
+    parser.add_argument(
+        "--summary-star",
+        action=argparse.BooleanOptionalAction,
+        default=False,
+        help="Pass to generate_video_with_labels: whether the summary line should draw *.",
+    )
 
     args = parser.parse_args()
     if args.frame_stride < 1:

FishMeasure/runs/train/fish_detection_20251127_104658/args.yaml

@@ -1,106 +0,0 @@
-task: detect
-mode: train
-model: yolov8n.pt
-data: ./yolo_dataset/dataset.yaml
-epochs: 100
-time: null
-patience: 50
-batch: 96
-imgsz: 640
-save: true
-save_period: -1
-cache: false
-device: null
-workers: 8
-project: runs/train
-name: fish_detection_20251127_104658
-exist_ok: false
-pretrained: false
-optimizer: auto
-verbose: true
-seed: 0
-deterministic: true
-single_cls: false
-rect: false
-cos_lr: false
-close_mosaic: 10
-resume: false
-amp: true
-fraction: 1.0
-profile: false
-freeze: null
-multi_scale: false
-overlap_mask: true
-mask_ratio: 4
-dropout: 0.0
-val: true
-split: val
-save_json: false
-save_hybrid: false
-conf: null
-iou: 0.7
-max_det: 300
-half: false
-dnn: false
-plots: true
-source: null
-vid_stride: 1
-stream_buffer: false
-visualize: false
-augment: false
-agnostic_nms: false
-classes: null
-retina_masks: false
-embed: null
-show: false
-save_frames: false
-save_txt: false
-save_conf: false
-save_crop: false
-show_labels: true
-show_conf: true
-show_boxes: true
-line_width: null
-format: torchscript
-keras: false
-optimize: false
-int8: false
-dynamic: false
-simplify: true
-opset: null
-workspace: null
-nms: false
-lr0: 0.01
-lrf: 0.01
-momentum: 0.937
-weight_decay: 0.0005
-warmup_epochs: 3.0
-warmup_momentum: 0.8
-warmup_bias_lr: 0.1
-box: 1.75
-cls: 0.5
-dfl: 1.5
-pose: 12.0
-kobj: 1.0
-nbs: 64
-hsv_h: 0.015
-hsv_s: 0.7
-hsv_v: 0.4
-degrees: 10.0
-translate: 0.2
-scale: 0.5
-shear: 2.0
-perspective: 0.0
-flipud: 0.1
-fliplr: 0.5
-bgr: 0.0
-mosaic: 1.0
-mixup: 0.2
-copy_paste: 0.3
-copy_paste_mode: flip
-auto_augment: randaugment
-erasing: 0.4
-crop_fraction: 1.0
-cfg: null
-tracker: botsort.yaml
-save_dir: runs/train/fish_detection_20251127_104658

FishMeasure/runs/train/fish_detection_20251127_104658/results.csv

@@ -1,101 +0,0 @@
-epoch,time,train/box_loss,train/cls_loss,train/dfl_loss,metrics/precision(B),metrics/recall(B),metrics/mAP50(B),metrics/mAP50-95(B),val/box_loss,val/cls_loss,val/dfl_loss,lr/pg0,lr/pg1,lr/pg2
-1,10.3904,0.39855,2.68593,1.4848,1,0.29733,0.96537,0.56943,0.33362,2.56495,1.02233,0.00038,0.00038,0.00038
-2,17.5483,0.30028,1.35659,1.12817,1,0.49396,0.95678,0.49421,0.35142,2.66289,1.12329,0.000772278,0.000772278,0.000772278
-3,25.1797,0.29352,1.17269,1.13078,0.63354,0.70588,0.71908,0.35996,0.3706,1.94815,1.15705,0.00115664,0.00115664,0.00115664
-4,31.2751,0.29379,1.05877,1.14652,0.92901,0.76994,0.8997,0.51519,0.34598,1.68774,1.25469,0.00153307,0.00153307,0.00153307
-5,38.2345,0.30129,1.01013,1.16273,1,0.05809,0.11957,0.0573,0.56052,3.3705,2.25768,0.00190159,0.00190159,0.00190159
-6,44.1377,0.29631,0.9286,1.17263,0.77814,0.72549,0.77275,0.49905,0.30463,2.21664,1.22409,0.001901,0.001901,0.001901
-7,51.7031,0.28969,0.82499,1.16157,0.81899,0.82353,0.86643,0.50327,0.30846,1.06156,1.23743,0.0018812,0.0018812,0.0018812
-8,57.6974,0.28756,0.79748,1.16646,0.97759,0.85543,0.93703,0.54512,0.30945,1.3021,1.15419,0.0018614,0.0018614,0.0018614
-9,64.6096,0.28988,0.78404,1.16845,0.87355,0.54195,0.61651,0.44007,0.28541,1.8088,1.19646,0.0018416,0.0018416,0.0018416
-10,70.8722,0.28509,0.74823,1.17001,1,0.97714,0.9879,0.66339,0.27556,0.67389,1.10534,0.0018218,0.0018218,0.0018218
-11,77.6729,0.2811,0.71605,1.16472,0.97131,1,0.99327,0.68686,0.26039,0.53918,1.12841,0.001802,0.001802,0.001802
-12,83.6789,0.27956,0.71366,1.17215,0.94349,0.7451,0.81617,0.36975,0.44564,1.10381,1.5902,0.0017822,0.0017822,0.0017822
-13,90.5196,0.27954,0.70341,1.16105,0.98977,0.98039,0.99395,0.70985,0.26287,0.71862,1.08777,0.0017624,0.0017624,0.0017624
-14,96.2279,0.27389,0.69109,1.16035,0.99776,0.98039,0.99481,0.68656,0.27765,0.65545,1.09127,0.0017426,0.0017426,0.0017426
-15,103.274,0.27484,0.69505,1.16409,0.94274,0.96857,0.98537,0.6647,0.2812,0.56622,1.11215,0.0017228,0.0017228,0.0017228
-16,109.28,0.27709,0.68435,1.17154,0.99813,0.98039,0.99462,0.71965,0.24753,0.50567,1.06086,0.001703,0.001703,0.001703
-17,116.354,0.27127,0.65515,1.15472,0.99011,0.96078,0.99405,0.68376,0.27062,0.59393,1.10243,0.0016832,0.0016832,0.0016832
-18,121.994,0.27291,0.65216,1.1543,0.97318,0.98039,0.99153,0.72137,0.24675,0.73777,1.04403,0.0016634,0.0016634,0.0016634
-19,128.471,0.27609,0.64481,1.1633,0.99856,1,0.995,0.71822,0.2506,0.44838,1.04764,0.0016436,0.0016436,0.0016436
-20,134.908,0.26641,0.63605,1.13566,0.97925,0.98039,0.99423,0.73946,0.22498,0.4882,1.01436,0.0016238,0.0016238,0.0016238
-21,141.659,0.27002,0.63276,1.15338,0.99622,1,0.995,0.73392,0.24781,0.6929,1.06027,0.001604,0.001604,0.001604
-22,147.596,0.27016,0.62133,1.15598,1,0.71878,0.7985,0.38994,0.43809,1.15961,1.45966,0.0015842,0.0015842,0.0015842
-23,154.606,0.26856,0.63903,1.14822,0.99006,0.96078,0.98976,0.73202,0.23704,0.89525,1.02748,0.0015644,0.0015644,0.0015644
-24,160.874,0.26556,0.61805,1.14759,0.52381,0.21569,0.37119,0.23923,0.48324,4.161,1.79371,0.0015446,0.0015446,0.0015446
-25,167.63,0.26283,0.62175,1.14417,0.99771,0.98039,0.99481,0.54043,0.36833,0.62126,1.2961,0.0015248,0.0015248,0.0015248
-26,172.972,0.26277,0.62184,1.14693,0.97588,0.79352,0.838,0.60246,0.26723,1.16324,1.14688,0.001505,0.001505,0.001505
-27,180.886,0.25845,0.58391,1.1274,1,0.97466,0.99444,0.7358,0.23001,0.43927,1.03289,0.0014852,0.0014852,0.0014852
-28,186.475,0.25736,0.59062,1.13027,0.99938,1,0.995,0.77511,0.22035,0.41332,1.01175,0.0014654,0.0014654,0.0014654
-29,193.178,0.25997,0.59153,1.13884,0.99623,1,0.995,0.72041,0.2431,0.43747,1.04154,0.0014456,0.0014456,0.0014456
-30,198.402,0.26318,0.59378,1.14352,0.99588,0.98039,0.99086,0.71822,0.23253,0.59404,1.04641,0.0014258,0.0014258,0.0014258
-31,204.755,0.25794,0.57997,1.12954,0.99758,1,0.995,0.65546,0.2929,0.53569,1.17732,0.001406,0.001406,0.001406
-32,210.705,0.25981,0.59023,1.14197,0.99123,0.96078,0.97752,0.7113,0.24951,0.53056,1.04465,0.0013862,0.0013862,0.0013862
-33,217.738,0.25927,0.58286,1.1443,0.99828,1,0.995,0.76497,0.21878,0.37529,1.00619,0.0013664,0.0013664,0.0013664
-34,223.275,0.25433,0.55825,1.11915,0.98879,0.84314,0.93602,0.58228,0.34063,0.70089,1.23218,0.0013466,0.0013466,0.0013466
-35,230.18,0.25841,0.5804,1.13861,0.99727,0.98039,0.9925,0.75134,0.21602,0.45677,1.00342,0.0013268,0.0013268,0.0013268
-36,236.28,0.2532,0.57095,1.13238,0.9975,0.98039,0.99093,0.74316,0.24353,0.43215,1.05353,0.001307,0.001307,0.001307
-37,243.19,0.25301,0.57535,1.13453,1,0.99155,0.995,0.72838,0.24188,0.67456,1.0605,0.0012872,0.0012872,0.0012872
-38,249.356,0.25509,0.56332,1.13272,1,0.95882,0.99102,0.74599,0.21894,0.44255,1.00044,0.0012674,0.0012674,0.0012674
-39,256.308,0.25554,0.5739,1.13027,0.99595,1,0.995,0.75996,0.22547,0.50187,1.01792,0.0012476,0.0012476,0.0012476
-40,262.306,0.25143,0.55879,1.12012,0.99711,1,0.995,0.76673,0.21535,0.46243,1.00072,0.0012278,0.0012278,0.0012278
-41,268.917,0.2534,0.56009,1.12077,0.99082,1,0.995,0.73951,0.23347,0.66055,1.02986,0.001208,0.001208,0.001208
-42,274.828,0.2489,0.5661,1.11458,1,0.91885,0.98684,0.72466,0.22931,0.53634,1.02747,0.0011882,0.0011882,0.0011882
-43,281.555,0.25301,0.55236,1.13143,0.99738,1,0.995,0.74646,0.2298,0.49582,1.02689,0.0011684,0.0011684,0.0011684
-44,287.74,0.2486,0.53306,1.11907,1,0.97736,0.99364,0.73858,0.23603,0.49003,1.03041,0.0011486,0.0011486,0.0011486
-45,294.836,0.24944,0.54158,1.1268,0.99062,1,0.995,0.75756,0.23048,0.60132,1.04024,0.0011288,0.0011288,0.0011288
-46,301.451,0.24913,0.53379,1.1269,0.99596,0.98039,0.99048,0.77386,0.20906,0.54314,0.99925,0.001109,0.001109,0.001109
-47,308.242,0.24957,0.53985,1.12517,0.99593,1,0.995,0.73996,0.23001,0.52276,1.02912,0.0010892,0.0010892,0.0010892
-48,314.344,0.24351,0.53626,1.10608,1,0.99956,0.995,0.74934,0.23199,0.39499,1.03412,0.0010694,0.0010694,0.0010694
-49,321.241,0.24759,0.53893,1.11816,1,0.99844,0.995,0.74604,0.22845,0.39064,1.02153,0.0010496,0.0010496,0.0010496
-50,327.139,0.2464,0.53694,1.1138,0.99835,0.98039,0.99048,0.71125,0.24541,0.42938,1.07937,0.0010298,0.0010298,0.0010298
-51,333.821,0.24154,0.51898,1.10733,0.99567,0.90196,0.97517,0.62595,0.29596,0.61014,1.14221,0.00101,0.00101,0.00101
-52,339.882,0.24658,0.53043,1.11979,0.99546,0.98039,0.99323,0.65978,0.27159,0.52309,1.13272,0.0009902,0.0009902,0.0009902
-53,346.689,0.24636,0.52582,1.11253,0.99778,0.98039,0.99481,0.69862,0.26351,0.45512,1.08185,0.0009704,0.0009704,0.0009704
-54,352.945,0.24152,0.51738,1.10331,0.99739,1,0.995,0.72452,0.24969,0.40628,1.06735,0.0009506,0.0009506,0.0009506
-55,359.178,0.24263,0.50863,1.10604,0.99683,1,0.995,0.77739,0.21597,0.42763,1.01173,0.0009308,0.0009308,0.0009308
-56,365.965,0.24373,0.51169,1.10391,0.95858,0.90771,0.97651,0.63893,0.29309,0.63256,1.16514,0.000911,0.000911,0.000911
-57,372.475,0.24282,0.51188,1.10565,0.9915,0.98039,0.99054,0.75734,0.21952,0.56379,1.01633,0.0008912,0.0008912,0.0008912
-58,379.602,0.23912,0.50781,1.09877,1,0.95988,0.98778,0.72449,0.24914,0.46787,1.05661,0.0008714,0.0008714,0.0008714
-59,385.13,0.24179,0.51076,1.10568,1,0.95731,0.98289,0.71162,0.23833,0.6395,1.04927,0.0008516,0.0008516,0.0008516
-60,392.571,0.23757,0.50074,1.09636,0.99702,0.98039,0.99261,0.76777,0.20872,0.47718,0.99627,0.0008318,0.0008318,0.0008318
-61,397.864,0.23342,0.49493,1.09485,0.99568,0.98039,0.9931,0.76937,0.20784,0.45567,1.01043,0.000812,0.000812,0.000812
-62,405.506,0.23929,0.49675,1.10508,0.9953,0.96078,0.9827,0.72038,0.24622,0.5664,1.07435,0.0007922,0.0007922,0.0007922
-63,411.243,0.2385,0.49568,1.09486,0.99783,0.98039,0.99086,0.76087,0.22259,0.49003,1.01614,0.0007724,0.0007724,0.0007724
-64,418.044,0.23775,0.49129,1.08891,0.99544,0.98039,0.99054,0.77224,0.21441,0.51803,1.00319,0.0007526,0.0007526,0.0007526
-65,423.941,0.23656,0.49423,1.09174,0.97965,0.94412,0.98937,0.76534,0.21473,0.53841,0.99562,0.0007328,0.0007328,0.0007328
-66,430.931,0.23491,0.49057,1.08267,0.99223,0.98039,0.98955,0.76326,0.21453,0.64708,0.99581,0.000713,0.000713,0.000713
-67,436.831,0.23603,0.4875,1.08431,0.99649,0.98039,0.99427,0.76543,0.21578,0.47111,0.99195,0.0006932,0.0006932,0.0006932
-68,443.698,0.23371,0.48684,1.08189,1,0.97435,0.99379,0.77164,0.215,0.53772,0.99543,0.0006734,0.0006734,0.0006734
-69,449.871,0.23341,0.48312,1.0883,0.99289,0.98039,0.99379,0.78205,0.20299,0.46992,0.97694,0.0006536,0.0006536,0.0006536
-70,456.649,0.2335,0.48756,1.08284,0.99768,0.98039,0.9931,0.76909,0.21567,0.3792,0.99144,0.0006338,0.0006338,0.0006338
-71,462.607,0.22882,0.47871,1.07799,0.99471,0.98039,0.991,0.76463,0.22008,0.44229,1.00736,0.000614,0.000614,0.000614
-72,469.768,0.23333,0.48255,1.08936,0.99842,0.92157,0.95471,0.6835,0.25689,0.5887,1.10088,0.0005942,0.0005942,0.0005942
-73,476.152,0.22814,0.47147,1.07796,0.99695,0.96078,0.99179,0.75486,0.22212,0.48941,1.01634,0.0005744,0.0005744,0.0005744
-74,483.377,0.22914,0.47235,1.08384,1,0.97669,0.9901,0.77219,0.2153,0.39275,0.99558,0.0005546,0.0005546,0.0005546
-75,488.716,0.22821,0.47539,1.08204,0.99868,1,0.995,0.74383,0.23322,0.39742,1.03818,0.0005348,0.0005348,0.0005348
-76,496.052,0.22693,0.47841,1.0774,0.9966,0.98039,0.99427,0.77597,0.22186,0.42881,1.00906,0.000515,0.000515,0.000515
-77,501.774,0.2272,0.46429,1.07859,0.99656,0.98039,0.9925,0.7684,0.21909,0.4223,1.00152,0.0004952,0.0004952,0.0004952
-78,508.605,0.22715,0.46817,1.08007,1,0.99833,0.995,0.77597,0.20663,0.39658,0.98381,0.0004754,0.0004754,0.0004754
-79,514.483,0.22845,0.46984,1.08602,0.99476,0.98039,0.99297,0.76487,0.22367,0.53976,1.01338,0.0004556,0.0004556,0.0004556
-80,521.104,0.22489,0.45308,1.07029,0.99378,0.98039,0.99364,0.76591,0.22644,0.44335,1.01611,0.0004358,0.0004358,0.0004358
-81,526.831,0.22808,0.46696,1.08249,0.9984,0.98039,0.99043,0.76392,0.22464,0.40558,1.00919,0.000416,0.000416,0.000416
-82,534.261,0.22461,0.45758,1.07345,0.99706,0.98039,0.9918,0.76203,0.22683,0.37658,1.02904,0.0003962,0.0003962,0.0003962
-83,539.83,0.2224,0.45574,1.06465,0.9966,0.96078,0.98809,0.77183,0.22791,0.58994,1.00929,0.0003764,0.0003764,0.0003764
-84,547.068,0.22321,0.45489,1.07012,0.99534,0.98039,0.99218,0.77586,0.21211,0.4875,0.99631,0.0003566,0.0003566,0.0003566
-85,553.422,0.22324,0.44994,1.07037,0.99705,0.98039,0.99122,0.77203,0.21439,0.42988,1.00439,0.0003368,0.0003368,0.0003368
-86,560.244,0.22593,0.46254,1.07436,0.99551,0.98039,0.99323,0.7568,0.21436,0.39946,1.00288,0.000317,0.000317,0.000317
-87,566.207,0.22535,0.45462,1.07467,0.99768,0.98039,0.99427,0.77229,0.20736,0.36008,0.99378,0.0002972,0.0002972,0.0002972
-88,573.201,0.22031,0.44716,1.0635,0.99697,0.98039,0.99481,0.76489,0.21791,0.38311,1.01245,0.0002774,0.0002774,0.0002774
-89,579.084,0.22289,0.44359,1.06804,0.99621,0.98039,0.99162,0.77105,0.21459,0.41661,0.99051,0.0002576,0.0002576,0.0002576
-90,585.517,0.2213,0.4519,1.07424,0.99675,0.98039,0.99122,0.76516,0.21041,0.42833,0.99584,0.0002378,0.0002378,0.0002378
-91,597.175,0.19679,0.38958,1.03361,0.99618,0.98039,0.9925,0.76415,0.21165,0.41842,0.98503,0.000218,0.000218,0.000218
-92,603.128,0.19341,0.33723,1.01494,0.99613,0.98039,0.99285,0.76376,0.21456,0.42319,0.99363,0.0001982,0.0001982,0.0001982
-93,609.58,0.19245,0.34007,1.02201,0.99697,0.98039,0.99229,0.76732,0.21373,0.38196,0.99964,0.0001784,0.0001784,0.0001784
-94,614.558,0.18975,0.33377,1.01562,0.99702,0.98039,0.99285,0.76477,0.21757,0.39742,0.9974,0.0001586,0.0001586,0.0001586
-95,620.215,0.18952,0.32777,1.01532,0.9962,0.98039,0.99107,0.7668,0.21387,0.44539,1.0045,0.0001388,0.0001388,0.0001388
-96,625.105,0.1894,0.32969,1.01349,0.99492,0.98039,0.9913,0.76397,0.21124,0.43134,0.99738,0.000119,0.000119,0.000119
-97,630.785,0.18892,0.32829,1.00956,0.99236,0.98039,0.9908,0.7635,0.21104,0.4798,0.99472,9.92e-05,9.92e-05,9.92e-05
-98,636.519,0.18811,0.32653,1.00609,0.99603,0.98039,0.99261,0.77306,0.21321,0.40139,0.99426,7.94e-05,7.94e-05,7.94e-05
-99,642.554,0.1863,0.32067,1.00634,0.99516,0.98039,0.9935,0.75723,0.21665,0.41315,1.00323,5.96e-05,5.96e-05,5.96e-05
-100,647.259,0.18644,0.31964,1.00625,0.99453,0.98039,0.99297,0.76087,0.21668,0.43148,1.00482,3.98e-05,3.98e-05,3.98e-05

FishMeasure/weight_estimator/test_dgcnn_weight_estimator.py

@@ -30,6 +30,24 @@ import re
 import sys
 import zlib
 from pathlib import Path
+
+if not hasattr(argparse, "BooleanOptionalAction"):
+    class _BooleanOptionalAction(argparse.Action):
+        def __init__(self, option_strings, dest, default=None, type=None,
+                     choices=None, required=False, help=None, metavar=None):
+            _option_strings = []
+            for opt in option_strings:
+                _option_strings.append(opt)
+                if opt.startswith("--"):
+                    _option_strings.append("--no-" + opt[2:])
+            super().__init__(option_strings=_option_strings, dest=dest, nargs=0,
+                             default=default, type=type, choices=choices,
+                             required=required, help=help, metavar=metavar)
+
+        def __call__(self, parser, namespace, values, option_string=None):
+            setattr(namespace, self.dest, not option_string.startswith("--no-"))
+
+    argparse.BooleanOptionalAction = _BooleanOptionalAction
 from typing import Any, Dict, List, Optional, Tuple
 
 import numpy as np