Upload 21 files

Added plots and training script and YAML

.gitattributes

@@ -33,3 +33,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+BoxF1_curve.png filter=lfs diff=lfs merge=lfs -text
+BoxP_curve.png filter=lfs diff=lfs merge=lfs -text
+BoxPR_curve.png filter=lfs diff=lfs merge=lfs -text
+BoxR_curve.png filter=lfs diff=lfs merge=lfs -text
+confusion_matrix_normalized.png filter=lfs diff=lfs merge=lfs -text
+confusion_matrix.png filter=lfs diff=lfs merge=lfs -text
+labels.jpg filter=lfs diff=lfs merge=lfs -text
+results.png filter=lfs diff=lfs merge=lfs -text
+train_batch0.jpg filter=lfs diff=lfs merge=lfs -text
+train_batch1.jpg filter=lfs diff=lfs merge=lfs -text
+train_batch2.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch0_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch0_pred.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch1_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch1_pred.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch2_labels.jpg filter=lfs diff=lfs merge=lfs -text
+val_batch2_pred.jpg filter=lfs diff=lfs merge=lfs -text

args.yaml

@@ -0,0 +1,105 @@
+task: detect
+mode: train
+model: yolo11x.yaml
+data: /data/james/reduced_experiment/data6/benthic_supercategory_detector.yaml
+epochs: 100
+time: null
+patience: 15
+batch: 32
+imgsz: 640
+save: true
+save_period: -1
+cache: false
+device: '0'
+workers: 8
+project: null
+name: train
+exist_ok: false
+pretrained: yolo11x.pt
+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
+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: 7.5
+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: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+bgr: 0.0
+mosaic: 1.0
+mixup: 0.0
+cutmix: 0.0
+copy_paste: 0.0
+copy_paste_mode: flip
+auto_augment: randaugment
+erasing: 0.4
+cfg: null
+tracker: botsort.yaml
+save_dir: runs/detect/train

benthic_supercategory_detector.yaml

@@ -0,0 +1,33 @@
+train: /data/james/reduced_experiment/data6/images/train
+val: /data/james/reduced_experiment/data6/images/val
+test: /data/james/reduced_experiment/data6/images/test
+names:
+  0: Sea Anemones
+  1: Bony fishes
+  2: Flatfish
+  3: Eels
+  4: Gastropods
+  5: Sharks
+  6: Rays and Skates
+  7: Chimaeras
+  8: Sea stars
+  9: Feather stars and sea lilies
+  10: Sea cucumbers
+  11: Urchins
+  12: Glass sponges
+  13: Sea fans
+  14: Soft corals
+  15: Sea pens
+  16: Stony corals
+  17: Black corals
+  18: Crabs
+  19: Shrimps
+  20: Squat lobsters
+  21: Barnacles
+  22: Sea spiders
+  23: Worms
+  24: Brittle Stars
+  25: Tube-Dwelling Anemones
+  26: Demosponges 
+  27: Zoanthids
+  28: Clams

results.csv

@@ -0,0 +1,87 @@
+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
+1,510.554,1.30685,2.15905,1.16091,0.44353,0.41404,0.37588,0.24114,1.28053,1.59709,1.12829,0.00332991,0.00332991,0.00332991
+2,1017.27,1.28684,1.49255,1.12629,0.53222,0.46377,0.45652,0.29443,1.2561,1.35019,1.10536,0.00659728,0.00659728,0.00659728
+3,1519.22,1.36116,1.58479,1.16414,0.3943,0.27602,0.2387,0.14081,1.4931,2.03336,1.26294,0.00979865,0.00979865,0.00979865
+4,2022.53,1.40732,1.65977,1.19716,0.51103,0.40739,0.40502,0.25371,1.32934,1.45307,1.16041,0.009703,0.009703,0.009703
+5,2524.71,1.33949,1.49103,1.16751,0.48828,0.45338,0.43642,0.27284,1.28413,1.37177,1.13542,0.009604,0.009604,0.009604
+6,3027.32,1.29554,1.38126,1.1538,0.53645,0.49798,0.50462,0.32757,1.20891,1.22063,1.10976,0.009505,0.009505,0.009505
+7,3529.75,1.26947,1.30713,1.13668,0.54285,0.53327,0.5251,0.35011,1.18996,1.15897,1.10379,0.009406,0.009406,0.009406
+8,4034.11,1.24768,1.25562,1.13022,0.60596,0.5362,0.55886,0.37178,1.16186,1.10814,1.09093,0.009307,0.009307,0.009307
+9,4536.44,1.23034,1.22038,1.12064,0.56352,0.54574,0.5692,0.38294,1.15313,1.07449,1.08059,0.009208,0.009208,0.009208
+10,5038.76,1.21648,1.1786,1.113,0.62196,0.57598,0.59508,0.41022,1.12363,1.03143,1.07176,0.009109,0.009109,0.009109
+11,5541.38,1.19754,1.14579,1.1059,0.5835,0.57695,0.59718,0.40969,1.12129,1.02792,1.07083,0.00901,0.00901,0.00901
+12,6044.15,1.1868,1.12417,1.10507,0.58934,0.59779,0.6155,0.42634,1.10641,0.98573,1.06432,0.008911,0.008911,0.008911
+13,6546.74,1.17396,1.09692,1.09831,0.61435,0.59539,0.62902,0.43504,1.09882,0.96664,1.06171,0.008812,0.008812,0.008812
+14,7050.07,1.16975,1.07866,1.0933,0.60353,0.62017,0.63471,0.44337,1.09238,0.95521,1.05389,0.008713,0.008713,0.008713
+15,7552.98,1.15805,1.06649,1.08789,0.62283,0.62513,0.64287,0.45053,1.0836,0.93621,1.05452,0.008614,0.008614,0.008614
+16,8056.31,1.15431,1.0454,1.08718,0.66376,0.60903,0.65264,0.45855,1.07368,0.9262,1.05265,0.008515,0.008515,0.008515
+17,8559.8,1.14377,1.02509,1.08117,0.65963,0.6216,0.64874,0.45766,1.06676,0.91424,1.04807,0.008416,0.008416,0.008416
+18,9063.86,1.13752,1.01792,1.08028,0.6665,0.62769,0.66195,0.46888,1.05973,0.90473,1.04425,0.008317,0.008317,0.008317
+19,9567.09,1.13613,1.0084,1.07918,0.63458,0.62841,0.66378,0.47306,1.05678,0.89485,1.04546,0.008218,0.008218,0.008218
+20,10071.2,1.12076,0.9888,1.07386,0.63218,0.63397,0.66521,0.47502,1.05656,0.88554,1.04396,0.008119,0.008119,0.008119
+21,10575.2,1.11559,0.97077,1.07101,0.65344,0.63715,0.67231,0.48005,1.05116,0.87498,1.04015,0.00802,0.00802,0.00802
+22,11079,1.11356,0.9633,1.06862,0.64702,0.63885,0.67195,0.48193,1.04521,0.87449,1.04102,0.007921,0.007921,0.007921
+23,11581.9,1.1101,0.95435,1.06664,0.63486,0.64412,0.67473,0.48423,1.04586,0.86954,1.04058,0.007822,0.007822,0.007822
+24,12086.4,1.10676,0.94542,1.06272,0.64733,0.64905,0.67977,0.48922,1.04256,0.86422,1.03846,0.007723,0.007723,0.007723
+25,12590.6,1.09599,0.93515,1.05843,0.65794,0.64682,0.67949,0.48827,1.04221,0.8617,1.03735,0.007624,0.007624,0.007624
+26,13094.1,1.09235,0.92512,1.05701,0.63741,0.66174,0.68231,0.48988,1.04043,0.85807,1.03593,0.007525,0.007525,0.007525
+27,13598.5,1.08785,0.91546,1.05384,0.62026,0.67472,0.68482,0.49345,1.03731,0.85311,1.03512,0.007426,0.007426,0.007426
+28,14102.9,1.08087,0.90302,1.04947,0.62051,0.67608,0.68471,0.49376,1.0361,0.85043,1.03326,0.007327,0.007327,0.007327
+29,14605.2,1.08046,0.89752,1.05356,0.62819,0.67914,0.68569,0.49519,1.0361,0.85112,1.03425,0.007228,0.007228,0.007228
+30,15106.8,1.07106,0.88671,1.04584,0.65487,0.65729,0.68619,0.49574,1.03416,0.85078,1.03282,0.007129,0.007129,0.007129
+31,15607.6,1.06974,0.88124,1.04637,0.65928,0.65613,0.6863,0.49723,1.03398,0.85012,1.03261,0.00703,0.00703,0.00703
+32,16108.9,1.06477,0.87268,1.04426,0.65815,0.66032,0.68678,0.49856,1.03361,0.84915,1.03294,0.006931,0.006931,0.006931
+33,16609.8,1.06225,0.86577,1.0412,0.66294,0.65978,0.68715,0.49847,1.03342,0.84755,1.03317,0.006832,0.006832,0.006832
+34,17111.5,1.05375,0.85422,1.03709,0.66591,0.66197,0.68842,0.50029,1.03273,0.84595,1.03246,0.006733,0.006733,0.006733
+35,17612.4,1.04974,0.84999,1.0371,0.66308,0.66147,0.68922,0.50078,1.03166,0.84467,1.0321,0.006634,0.006634,0.006634
+36,18114.5,1.04413,0.8383,1.0363,0.66837,0.65858,0.68955,0.50131,1.03134,0.84395,1.03206,0.006535,0.006535,0.006535
+37,18615.8,1.04017,0.8319,1.03218,0.66578,0.66159,0.69003,0.50231,1.03121,0.84268,1.03221,0.006436,0.006436,0.006436
+38,19118.2,1.03658,0.82061,1.02887,0.67257,0.65711,0.69048,0.50193,1.03056,0.84151,1.03197,0.006337,0.006337,0.006337
+39,19619.4,1.03593,0.82018,1.02986,0.67072,0.65973,0.69102,0.50235,1.03043,0.84057,1.03206,0.006238,0.006238,0.006238
+40,20120.8,1.02588,0.81129,1.02611,0.6526,0.67487,0.69088,0.50273,1.03016,0.83991,1.03195,0.006139,0.006139,0.006139
+41,20622,1.02525,0.79951,1.02294,0.65118,0.67735,0.69085,0.50256,1.03008,0.83948,1.03187,0.00604,0.00604,0.00604
+42,21123.8,1.02172,0.79641,1.0229,0.6572,0.67094,0.69107,0.50269,1.02945,0.83909,1.03146,0.005941,0.005941,0.005941
+43,21625,1.01192,0.78632,1.01897,0.6611,0.66762,0.69123,0.50268,1.02944,0.83868,1.03148,0.005842,0.005842,0.005842
+44,22126.3,1.01056,0.77964,1.01938,0.66352,0.66294,0.69115,0.50246,1.02917,0.83793,1.03162,0.005743,0.005743,0.005743
+45,22627,1.00724,0.7758,1.01725,0.65565,0.66823,0.69196,0.50299,1.0291,0.83781,1.03193,0.005644,0.005644,0.005644
+46,23129.8,1.00286,0.7697,1.0171,0.6574,0.66802,0.69199,0.50345,1.0283,0.83685,1.03187,0.005545,0.005545,0.005545
+47,23631.4,0.99786,0.75934,1.01523,0.64982,0.67067,0.69199,0.50421,1.02803,0.83618,1.03194,0.005446,0.005446,0.005446
+48,24133.6,0.9946,0.75655,1.01117,0.65606,0.67289,0.69214,0.50451,1.02815,0.83567,1.03191,0.005347,0.005347,0.005347
+49,24635.2,0.98705,0.7457,1.01128,0.65131,0.67489,0.69213,0.50508,1.02824,0.83474,1.03217,0.005248,0.005248,0.005248
+50,25137.1,0.98114,0.74137,1.00628,0.65281,0.67363,0.69235,0.50493,1.02816,0.83429,1.03207,0.005149,0.005149,0.005149
+51,25638.5,0.97807,0.72968,1.00383,0.65615,0.67532,0.69231,0.50515,1.02811,0.83359,1.03229,0.00505,0.00505,0.00505
+52,26140.4,0.97351,0.7209,0.99916,0.65387,0.67617,0.69284,0.50556,1.02819,0.83309,1.03236,0.004951,0.004951,0.004951
+53,26642.3,0.9681,0.71641,1.00145,0.66045,0.67171,0.69318,0.50591,1.02827,0.83259,1.03255,0.004852,0.004852,0.004852
+54,27145.2,0.96786,0.71513,1.0004,0.66386,0.66794,0.69358,0.50604,1.02847,0.83189,1.0328,0.004753,0.004753,0.004753
+55,27647,0.95948,0.70065,0.99483,0.66463,0.66884,0.69346,0.50588,1.02828,0.83126,1.0329,0.004654,0.004654,0.004654
+56,28148.4,0.95033,0.69389,0.99554,0.66562,0.67007,0.69344,0.50611,1.02805,0.83043,1.03291,0.004555,0.004555,0.004555
+57,28649.5,0.94768,0.68838,0.99279,0.66689,0.67135,0.69361,0.50673,1.02803,0.82963,1.03319,0.004456,0.004456,0.004456
+58,29151.6,0.94205,0.6821,0.98967,0.66805,0.6716,0.6938,0.50672,1.0282,0.82896,1.03333,0.004357,0.004357,0.004357
+59,29654.8,0.93964,0.67908,0.98769,0.67152,0.66761,0.69442,0.50747,1.02792,0.82863,1.03312,0.004258,0.004258,0.004258
+60,30158.7,0.93193,0.66423,0.98654,0.6787,0.66411,0.6946,0.50785,1.02799,0.82823,1.03351,0.004159,0.004159,0.004159
+61,30662,0.92707,0.66051,0.9856,0.68397,0.6637,0.69488,0.50829,1.02851,0.82775,1.03412,0.00406,0.00406,0.00406
+62,31165.7,0.92242,0.65154,0.98049,0.68331,0.66612,0.69496,0.50823,1.02883,0.82718,1.03454,0.003961,0.003961,0.003961
+63,31668.3,0.91847,0.64737,0.97977,0.67874,0.67037,0.69513,0.50862,1.02905,0.8272,1.03493,0.003862,0.003862,0.003862
+64,32171.9,0.91175,0.63783,0.97596,0.68245,0.66632,0.6954,0.50858,1.02927,0.82665,1.0351,0.003763,0.003763,0.003763
+65,32674.8,0.90749,0.63245,0.97551,0.68432,0.66377,0.69516,0.50835,1.02993,0.82654,1.03539,0.003664,0.003664,0.003664
+66,33178,0.90323,0.62658,0.97675,0.67974,0.66752,0.69505,0.50819,1.03026,0.82656,1.036,0.003565,0.003565,0.003565
+67,33681.2,0.89664,0.61974,0.96986,0.67276,0.67294,0.6951,0.50849,1.03052,0.82663,1.03641,0.003466,0.003466,0.003466
+68,34185.1,0.89004,0.6136,0.96812,0.67439,0.67397,0.69531,0.50824,1.03084,0.82694,1.03663,0.003367,0.003367,0.003367
+69,34688,0.88526,0.60789,0.96877,0.67402,0.67407,0.69527,0.50899,1.03097,0.82716,1.03693,0.003268,0.003268,0.003268
+70,35191.6,0.87945,0.60033,0.96206,0.66435,0.67416,0.69525,0.50885,1.03124,0.8281,1.037,0.003169,0.003169,0.003169
+71,35695,0.87607,0.59462,0.96056,0.66396,0.6745,0.69555,0.50947,1.03163,0.82885,1.03711,0.00307,0.00307,0.00307
+72,36198.5,0.86472,0.58419,0.95745,0.6672,0.67195,0.69537,0.50903,1.03215,0.82959,1.03741,0.002971,0.002971,0.002971
+73,36702,0.8621,0.57787,0.95596,0.66833,0.6744,0.69535,0.50892,1.0324,0.83019,1.03756,0.002872,0.002872,0.002872
+74,37205.8,0.85442,0.56731,0.95428,0.6722,0.67286,0.69487,0.50873,1.03286,0.83105,1.0377,0.002773,0.002773,0.002773
+75,37709.6,0.84689,0.56383,0.95088,0.6772,0.67005,0.69473,0.50885,1.03352,0.83235,1.03814,0.002674,0.002674,0.002674
+76,38213.9,0.83959,0.55903,0.94793,0.67615,0.66983,0.69462,0.50872,1.0339,0.83386,1.0384,0.002575,0.002575,0.002575
+77,38716.9,0.83483,0.54678,0.94539,0.67405,0.66972,0.69429,0.50839,1.03452,0.83588,1.03897,0.002476,0.002476,0.002476
+78,39220.3,0.82763,0.54378,0.94146,0.67456,0.66655,0.6943,0.50865,1.03505,0.83764,1.03894,0.002377,0.002377,0.002377
+79,39724.6,0.82625,0.54034,0.93981,0.67129,0.66825,0.69374,0.50847,1.03558,0.83948,1.03891,0.002278,0.002278,0.002278
+80,40228.6,0.81373,0.52765,0.93614,0.66974,0.67239,0.69367,0.50877,1.03617,0.84189,1.03887,0.002179,0.002179,0.002179
+81,40731.6,0.81166,0.52264,0.93616,0.67166,0.66865,0.69333,0.50872,1.03681,0.84447,1.0391,0.00208,0.00208,0.00208
+82,41235.6,0.80028,0.51377,0.93028,0.67609,0.66681,0.69317,0.50798,1.03787,0.84739,1.03964,0.001981,0.001981,0.001981
+83,41739,0.79979,0.51254,0.93376,0.67428,0.66829,0.69293,0.50795,1.03873,0.85094,1.04023,0.001882,0.001882,0.001882
+84,42242.5,0.79001,0.50439,0.92741,0.67557,0.66592,0.69234,0.50754,1.03973,0.85417,1.04065,0.001783,0.001783,0.001783
+85,42745.9,0.78282,0.49551,0.9286,0.67609,0.6652,0.69187,0.50714,1.04067,0.85733,1.04136,0.001684,0.001684,0.001684
+86,43249.3,0.77527,0.49049,0.92442,0.68484,0.65681,0.69147,0.50689,1.04178,0.86059,1.04207,0.001585,0.001585,0.001585

train.py

@@ -0,0 +1,25 @@
+# %pip install comet_ml --quiet
+import comet_ml
+import torch
+from ultralytics import YOLO
+import ultralytics.data as data
+import ultralytics.data.dataset as dataset
+import ultralytics.data.build as build
+
+import numpy as np
+comet_ml.login(project_name='reduced_images_benthic_supercategory_detector6')
+#comet_ml.start(mode="get", experiment_keyd="87329baa84f547feb8f249cd3991b51d")
+
+import os
+os.environ["CUDA_VISIBLE_DEVICES"] = "1"
+
+print("CUDA Available:", torch.cuda.is_available())
+if torch.cuda.is_available():
+        print("GPU Name:", torch.cuda.get_device_name(0))
+
+
+model = YOLO("yolo11x.yaml")
+model = YOLO("yolo11x.pt")  # Load a pretrained model
+model = YOLO("yolo11x.yaml").load("yolo11x.pt")
+
+results = model.train(data='/data/james/reduced_experiment/data6/benthic_supercategory_detector.yaml', batch = 32, epochs=100, imgsz=640, patience=15, val=True, device=0, plots=True)