--- language: - eng license: cc0-1.0 tags: - multilabel-image-classification - multilabel - generated_from_trainer base_model: drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs model-index: - name: drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs results: [] --- drone-DinoVdeau-from-probs is a fine-tuned version of [drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs](https://huggingface.co/drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs). It achieves the following results on the test set: - Loss: 0.4668 - RMSE: 0.1546 - MAE: 0.1143 - KL Divergence: 0.3931 --- # Model description drone-DinoVdeau-from-probs is a model built on top of drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs model for underwater multilabel image classification.The classification head is a combination of linear, ReLU, batch normalization, and dropout layers. The source code for training the model can be found in this [Git repository](https://github.com/SeatizenDOI/DinoVdeau). - **Developed by:** [lombardata](https://huggingface.co/lombardata), credits to [César Leblanc](https://huggingface.co/CesarLeblanc) and [Victor Illien](https://huggingface.co/groderg) --- # Intended uses & limitations You can use the raw model for classify diverse marine species, encompassing coral morphotypes classes taken from the Global Coral Reef Monitoring Network (GCRMN), habitats classes and seagrass species. --- # Training and evaluation data Details on the estimated number of images for each class are given in the following table: | Class | train | test | val | Total | |:------------------------|--------:|-------:|------:|--------:| | Acropore_branched | 1220 | 363 | 362 | 1945 | | Acropore_digitised | 586 | 195 | 189 | 970 | | Acropore_tabular | 308 | 133 | 119 | 560 | | Algae | 4777 | 1372 | 1384 | 7533 | | Dead_coral | 2513 | 671 | 693 | 3877 | | Millepore | 136 | 55 | 59 | 250 | | No_acropore_encrusting | 252 | 88 | 93 | 433 | | No_acropore_massive | 2158 | 725 | 726 | 3609 | | No_acropore_sub_massive | 2036 | 582 | 612 | 3230 | | Rock | 5976 | 1941 | 1928 | 9845 | | Rubble | 4851 | 1486 | 1474 | 7811 | | Sand | 6155 | 2019 | 1990 | 10164 | --- # Training procedure ## Training hyperparameters The following hyperparameters were used during training: - **Number of Epochs**: 83.0 - **Learning Rate**: 0.001 - **Train Batch Size**: 32 - **Eval Batch Size**: 32 - **Optimizer**: Adam - **LR Scheduler Type**: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1 - **Freeze Encoder**: Yes - **Data Augmentation**: Yes ## Data Augmentation Data were augmented using the following transformations : Train Transforms - **PreProcess**: No additional parameters - **Resize**: probability=1.00 - **RandomHorizontalFlip**: probability=0.25 - **RandomVerticalFlip**: probability=0.25 - **ColorJiggle**: probability=0.25 - **RandomPerspective**: probability=0.25 - **Normalize**: probability=1.00 Val Transforms - **PreProcess**: No additional parameters - **Resize**: probability=1.00 - **Normalize**: probability=1.00 ## Training results Epoch | Validation Loss | MAE | RMSE | KL div | Learning Rate --- | --- | --- | --- | --- | --- 1 | 0.4855400025844574 | 0.1364 | 0.1771 | 0.3101 | 0.001 2 | 0.47601452469825745 | 0.1247 | 0.1688 | 0.5077 | 0.001 3 | 0.4776814579963684 | 0.1230 | 0.1707 | 0.7896 | 0.001 4 | 0.47429159283638 | 0.1238 | 0.1672 | 0.4932 | 0.001 5 | 0.47457176446914673 | 0.1277 | 0.1669 | 0.2901 | 0.001 6 | 0.4749792814254761 | 0.1253 | 0.1674 | 0.4399 | 0.001 7 | 0.4744807779788971 | 0.1259 | 0.1671 | 0.4868 | 0.001 8 | 0.47424906492233276 | 0.1257 | 0.1672 | 0.3241 | 0.001 9 | 0.4729686379432678 | 0.1236 | 0.1658 | 0.4560 | 0.001 10 | 0.4750550389289856 | 0.1269 | 0.1679 | 0.2141 | 0.001 11 | 0.4733181595802307 | 0.1265 | 0.1663 | 0.2530 | 0.001 12 | 0.4758349061012268 | 0.1264 | 0.1684 | 0.3966 | 0.001 13 | 0.4722050428390503 | 0.1223 | 0.1650 | 0.6055 | 0.001 14 | 0.4747372567653656 | 0.1250 | 0.1666 | 0.4203 | 0.001 15 | 0.47325292229652405 | 0.1227 | 0.1662 | 0.6553 | 0.001 16 | 0.4734710156917572 | 0.1241 | 0.1656 | 0.3576 | 0.001 17 | 0.4721581041812897 | 0.1221 | 0.1643 | 0.4545 | 0.001 18 | 0.4723944365978241 | 0.1225 | 0.1647 | 0.4902 | 0.001 19 | 0.47289156913757324 | 0.1261 | 0.1650 | 0.3158 | 0.001 20 | 0.4697262644767761 | 0.1203 | 0.1623 | 0.4574 | 0.0001 21 | 0.46890661120414734 | 0.1197 | 0.1613 | 0.4569 | 0.0001 22 | 0.46905258297920227 | 0.1202 | 0.1617 | 0.4535 | 0.0001 23 | 0.4691086411476135 | 0.1210 | 0.1614 | 0.2971 | 0.0001 24 | 0.46915334463119507 | 0.1196 | 0.1616 | 0.3916 | 0.0001 25 | 0.4676876664161682 | 0.1181 | 0.1601 | 0.4516 | 0.0001 26 | 0.4679708480834961 | 0.1171 | 0.1605 | 0.6089 | 0.0001 27 | 0.4674595892429352 | 0.1182 | 0.1600 | 0.4741 | 0.0001 28 | 0.46810340881347656 | 0.1200 | 0.1606 | 0.3356 | 0.0001 29 | 0.4678303897380829 | 0.1181 | 0.1603 | 0.4330 | 0.0001 30 | 0.46800243854522705 | 0.1194 | 0.1602 | 0.3160 | 0.0001 31 | 0.4676785469055176 | 0.1179 | 0.1600 | 0.4190 | 0.0001 32 | 0.46752873063087463 | 0.1188 | 0.1598 | 0.3706 | 0.0001 33 | 0.46710190176963806 | 0.1181 | 0.1593 | 0.3504 | 0.0001 34 | 0.4670344293117523 | 0.1180 | 0.1594 | 0.3881 | 0.0001 35 | 0.4662601053714752 | 0.1166 | 0.1587 | 0.4398 | 0.0001 36 | 0.46657058596611023 | 0.1170 | 0.1587 | 0.4382 | 0.0001 37 | 0.4657588005065918 | 0.1163 | 0.1581 | 0.4330 | 0.0001 38 | 0.4659184217453003 | 0.1162 | 0.1583 | 0.4878 | 0.0001 39 | 0.46703553199768066 | 0.1178 | 0.1595 | 0.3791 | 0.0001 40 | 0.4664987027645111 | 0.1178 | 0.1588 | 0.3889 | 0.0001 41 | 0.46659526228904724 | 0.1184 | 0.1589 | 0.3222 | 0.0001 42 | 0.4655005633831024 | 0.1164 | 0.1579 | 0.4262 | 0.0001 43 | 0.4656265676021576 | 0.1162 | 0.1579 | 0.4611 | 0.0001 44 | 0.4655725955963135 | 0.1164 | 0.1580 | 0.4586 | 0.0001 45 | 0.46600833535194397 | 0.1158 | 0.1583 | 0.4368 | 0.0001 46 | 0.4660418927669525 | 0.1164 | 0.1582 | 0.4118 | 0.0001 47 | 0.46521857380867004 | 0.1154 | 0.1577 | 0.5424 | 0.0001 48 | 0.46598610281944275 | 0.1160 | 0.1586 | 0.5251 | 0.0001 49 | 0.46604350209236145 | 0.1161 | 0.1585 | 0.5007 | 0.0001 50 | 0.46660009026527405 | 0.1185 | 0.1586 | 0.2424 | 0.0001 51 | 0.4660661220550537 | 0.1162 | 0.1584 | 0.4171 | 0.0001 52 | 0.4649689793586731 | 0.1155 | 0.1575 | 0.4912 | 0.0001 53 | 0.4653578996658325 | 0.1169 | 0.1578 | 0.4030 | 0.0001 54 | 0.4660585820674896 | 0.1153 | 0.1585 | 0.4811 | 0.0001 55 | 0.46527624130249023 | 0.1167 | 0.1576 | 0.3774 | 0.0001 56 | 0.4654240906238556 | 0.1176 | 0.1575 | 0.3254 | 0.0001 57 | 0.4654492139816284 | 0.1162 | 0.1575 | 0.3649 | 0.0001 58 | 0.46654412150382996 | 0.1166 | 0.1584 | 0.4075 | 0.0001 59 | 0.465238481760025 | 0.1157 | 0.1575 | 0.4202 | 1e-05 60 | 0.46530231833457947 | 0.1157 | 0.1571 | 0.4084 | 1e-05 61 | 0.4653523564338684 | 0.1153 | 0.1573 | 0.4497 | 1e-05 62 | 0.46477487683296204 | 0.1153 | 0.1568 | 0.4112 | 1e-05 63 | 0.46481335163116455 | 0.1152 | 0.1567 | 0.3748 | 1e-05 64 | 0.46523070335388184 | 0.1162 | 0.1571 | 0.3044 | 1e-05 65 | 0.46484872698783875 | 0.1153 | 0.1569 | 0.4685 | 1e-05 66 | 0.46500927209854126 | 0.1148 | 0.1573 | 0.5087 | 1e-05 67 | 0.4645930230617523 | 0.1155 | 0.1568 | 0.4274 | 1e-05 68 | 0.46456360816955566 | 0.1144 | 0.1566 | 0.4969 | 1e-05 69 | 0.464430034160614 | 0.1145 | 0.1564 | 0.4480 | 1e-05 70 | 0.4648461937904358 | 0.1150 | 0.1567 | 0.4291 | 1e-05 71 | 0.4645022749900818 | 0.1156 | 0.1565 | 0.3797 | 1e-05 72 | 0.46473589539527893 | 0.1150 | 0.1569 | 0.4280 | 1e-05 73 | 0.46414923667907715 | 0.1142 | 0.1563 | 0.4592 | 1e-05 74 | 0.4641610085964203 | 0.1151 | 0.1564 | 0.4321 | 1e-05 75 | 0.4644509255886078 | 0.1152 | 0.1565 | 0.3843 | 1e-05 76 | 0.4646488130092621 | 0.1147 | 0.1569 | 0.5216 | 1e-05 77 | 0.46475714445114136 | 0.1152 | 0.1569 | 0.4094 | 1e-05 78 | 0.46428272128105164 | 0.1149 | 0.1564 | 0.4399 | 1e-05 79 | 0.4645934998989105 | 0.1147 | 0.1567 | 0.4178 | 1e-05 80 | 0.46436014771461487 | 0.1150 | 0.1564 | 0.4373 | 1.0000000000000002e-06 81 | 0.46448636054992676 | 0.1151 | 0.1567 | 0.4701 | 1.0000000000000002e-06 82 | 0.4644375145435333 | 0.1146 | 0.1565 | 0.4601 | 1.0000000000000002e-06 83 | 0.46457409858703613 | 0.1147 | 0.1567 | 0.4511 | 1.0000000000000002e-06 --- # Framework Versions - **Transformers**: 4.41.0 - **Pytorch**: 2.5.0+cu124 - **Datasets**: 3.0.2 - **Tokenizers**: 0.19.1