--- language: - eng license: cc0-1.0 tags: - multilabel-image-classification - multilabel - generated_from_trainer base_model: drone-DinoVdeau-from-probs-large-2024_11_14-batch-size16_freeze_probs model-index: - name: drone-DinoVdeau-from-probs-large-2024_11_14-batch-size16_freeze_probs results: [] --- drone-DinoVdeau-from-probs is a fine-tuned version of [drone-DinoVdeau-from-probs-large-2024_11_14-batch-size16_freeze_probs](https://huggingface.co/drone-DinoVdeau-from-probs-large-2024_11_14-batch-size16_freeze_probs). It achieves the following results on the test set: - Loss: 0.4672 - RMSE: 0.1550 - MAE: 0.1155 - KL Divergence: 0.3295 --- # Model description drone-DinoVdeau-from-probs is a model built on top of drone-DinoVdeau-from-probs-large-2024_11_14-batch-size16_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**: 94.0 - **Learning Rate**: 0.001 - **Train Batch Size**: 16 - **Eval Batch Size**: 16 - **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 | 0.4933677613735199 | 0.1294 | 0.1825 | 0.9903 | 0.001 2 | 0.47886165976524353 | 0.1262 | 0.1716 | 0.6847 | 0.001 3 | 0.4788369834423065 | 0.1271 | 0.1709 | 0.5498 | 0.001 4 | 0.47656363248825073 | 0.1278 | 0.1695 | 0.3131 | 0.001 5 | 0.4765072166919708 | 0.1277 | 0.1687 | 0.4013 | 0.001 6 | 0.47649845480918884 | 0.1243 | 0.1689 | 0.6370 | 0.001 7 | 0.47629299759864807 | 0.1292 | 0.1694 | 0.4314 | 0.001 8 | 0.4755041003227234 | 0.1267 | 0.1681 | 0.3379 | 0.001 9 | 0.47342246770858765 | 0.1250 | 0.1662 | 0.4916 | 0.001 10 | 0.47546806931495667 | 0.1277 | 0.1677 | 0.3348 | 0.001 11 | 0.4731104075908661 | 0.1255 | 0.1659 | 0.3524 | 0.001 12 | 0.47679492831230164 | 0.1306 | 0.1690 | 0.2383 | 0.001 13 | 0.4736888110637665 | 0.1223 | 0.1666 | 0.6968 | 0.001 14 | 0.4736703634262085 | 0.1254 | 0.1658 | 0.3983 | 0.001 15 | 0.4738818407058716 | 0.1248 | 0.1664 | 0.5620 | 0.001 16 | 0.47202879190444946 | 0.1231 | 0.1648 | 0.6049 | 0.001 17 | 0.47406336665153503 | 0.1265 | 0.1664 | 0.3072 | 0.001 18 | 0.4738321006298065 | 0.1253 | 0.1650 | 0.3350 | 0.001 19 | 0.476326048374176 | 0.1282 | 0.1672 | 0.2746 | 0.001 20 | 0.4755523204803467 | 0.1245 | 0.1670 | 0.5659 | 0.001 21 | 0.47340598702430725 | 0.1230 | 0.1662 | 0.6154 | 0.001 22 | 0.47443991899490356 | 0.1223 | 0.1677 | 0.7974 | 0.001 23 | 0.47205689549446106 | 0.1252 | 0.1639 | 0.2307 | 0.0001 24 | 0.4706146717071533 | 0.1217 | 0.1631 | 0.4219 | 0.0001 25 | 0.46876564621925354 | 0.1195 | 0.1612 | 0.5242 | 0.0001 26 | 0.46925392746925354 | 0.1190 | 0.1620 | 0.6159 | 0.0001 27 | 0.46849024295806885 | 0.1206 | 0.1607 | 0.4046 | 0.0001 28 | 0.46939656138420105 | 0.1220 | 0.1616 | 0.2860 | 0.0001 29 | 0.46892231702804565 | 0.1197 | 0.1614 | 0.4270 | 0.0001 30 | 0.46987923979759216 | 0.1225 | 0.1619 | 0.2625 | 0.0001 31 | 0.46842578053474426 | 0.1197 | 0.1607 | 0.3876 | 0.0001 32 | 0.46784707903862 | 0.1195 | 0.1600 | 0.4060 | 0.0001 33 | 0.46755874156951904 | 0.1193 | 0.1596 | 0.3688 | 0.0001 34 | 0.46766504645347595 | 0.1194 | 0.1600 | 0.3900 | 0.0001 35 | 0.4670174717903137 | 0.1189 | 0.1593 | 0.4282 | 0.0001 36 | 0.46679624915122986 | 0.1180 | 0.1591 | 0.4446 | 0.0001 37 | 0.46689239144325256 | 0.1185 | 0.1590 | 0.3942 | 0.0001 38 | 0.4664570987224579 | 0.1177 | 0.1588 | 0.4783 | 0.0001 39 | 0.4674011468887329 | 0.1190 | 0.1597 | 0.3868 | 0.0001 40 | 0.4677062928676605 | 0.1195 | 0.1599 | 0.3627 | 0.0001 41 | 0.46822381019592285 | 0.1211 | 0.1602 | 0.2655 | 0.0001 42 | 0.4664672613143921 | 0.1172 | 0.1589 | 0.5072 | 0.0001 43 | 0.46638762950897217 | 0.1177 | 0.1585 | 0.4306 | 0.0001 44 | 0.46708741784095764 | 0.1192 | 0.1594 | 0.4115 | 0.0001 45 | 0.46663177013397217 | 0.1171 | 0.1590 | 0.4417 | 0.0001 46 | 0.4663327634334564 | 0.1179 | 0.1585 | 0.3686 | 0.0001 47 | 0.46577510237693787 | 0.1172 | 0.1582 | 0.5090 | 0.0001 48 | 0.46634000539779663 | 0.1175 | 0.1589 | 0.5279 | 0.0001 49 | 0.46656596660614014 | 0.1183 | 0.1591 | 0.4497 | 0.0001 50 | 0.46755433082580566 | 0.1205 | 0.1595 | 0.2712 | 0.0001 51 | 0.46639156341552734 | 0.1172 | 0.1586 | 0.4008 | 0.0001 52 | 0.46591076254844666 | 0.1163 | 0.1583 | 0.4922 | 0.0001 53 | 0.4656851887702942 | 0.1178 | 0.1579 | 0.4274 | 0.0001 54 | 0.46629655361175537 | 0.1158 | 0.1585 | 0.4574 | 0.0001 55 | 0.46644341945648193 | 0.1189 | 0.1586 | 0.3486 | 0.0001 56 | 0.4661739766597748 | 0.1184 | 0.1584 | 0.3016 | 0.0001 57 | 0.46634721755981445 | 0.1181 | 0.1587 | 0.4163 | 0.0001 58 | 0.4673805236816406 | 0.1189 | 0.1593 | 0.3399 | 0.0001 59 | 0.4650005102157593 | 0.1170 | 0.1572 | 0.3686 | 0.0001 60 | 0.46599113941192627 | 0.1172 | 0.1584 | 0.4535 | 0.0001 61 | 0.4662201702594757 | 0.1179 | 0.1585 | 0.3751 | 0.0001 62 | 0.46614503860473633 | 0.1173 | 0.1583 | 0.3534 | 0.0001 63 | 0.4660026431083679 | 0.1163 | 0.1583 | 0.4048 | 0.0001 64 | 0.46711620688438416 | 0.1188 | 0.1588 | 0.2471 | 0.0001 65 | 0.46536803245544434 | 0.1166 | 0.1577 | 0.4526 | 0.0001 66 | 0.46573594212532043 | 0.1161 | 0.1582 | 0.5259 | 1e-05 67 | 0.4653942584991455 | 0.1173 | 0.1574 | 0.4252 | 1e-05 68 | 0.46487176418304443 | 0.1154 | 0.1572 | 0.4989 | 1e-05 69 | 0.465110719203949 | 0.1161 | 0.1570 | 0.4023 | 1e-05 70 | 0.466043084859848 | 0.1166 | 0.1576 | 0.4118 | 1e-05 71 | 0.46608996391296387 | 0.1177 | 0.1578 | 0.3075 | 1e-05 72 | 0.46582332253456116 | 0.1171 | 0.1580 | 0.3836 | 1e-05 73 | 0.4648771584033966 | 0.1154 | 0.1569 | 0.4544 | 1e-05 74 | 0.46466848254203796 | 0.1163 | 0.1567 | 0.4538 | 1e-05 75 | 0.46563470363616943 | 0.1166 | 0.1573 | 0.3348 | 1e-05 76 | 0.4647076725959778 | 0.1158 | 0.1571 | 0.4976 | 1e-05 77 | 0.4650570750236511 | 0.1163 | 0.1570 | 0.3934 | 1e-05 78 | 0.46495845913887024 | 0.1161 | 0.1571 | 0.3936 | 1e-05 79 | 0.46530288457870483 | 0.1159 | 0.1573 | 0.3759 | 1e-05 80 | 0.4647064805030823 | 0.1162 | 0.1567 | 0.4189 | 1e-05 81 | 0.46485888957977295 | 0.1158 | 0.1571 | 0.4751 | 1.0000000000000002e-06 82 | 0.4654049277305603 | 0.1161 | 0.1572 | 0.4335 | 1.0000000000000002e-06 83 | 0.46466442942619324 | 0.1161 | 0.1566 | 0.3906 | 1.0000000000000002e-06 84 | 0.46430692076683044 | 0.1157 | 0.1564 | 0.3855 | 1.0000000000000002e-06 85 | 0.46528080105781555 | 0.1173 | 0.1571 | 0.3372 | 1.0000000000000002e-06 86 | 0.46546733379364014 | 0.1184 | 0.1572 | 0.2969 | 1.0000000000000002e-06 87 | 0.4651782214641571 | 0.1173 | 0.1571 | 0.3572 | 1.0000000000000002e-06 88 | 0.4655611217021942 | 0.1151 | 0.1578 | 0.5179 | 1.0000000000000002e-06 89 | 0.4654468297958374 | 0.1177 | 0.1574 | 0.2948 | 1.0000000000000002e-06 90 | 0.4649873971939087 | 0.1167 | 0.1569 | 0.3427 | 1.0000000000000002e-06 91 | 0.4655340015888214 | 0.1173 | 0.1572 | 0.2790 | 1.0000000000000002e-07 92 | 0.4645555317401886 | 0.1153 | 0.1566 | 0.4153 | 1.0000000000000002e-07 93 | 0.4648568034172058 | 0.1153 | 0.1571 | 0.4664 | 1.0000000000000002e-07 94 | 0.4652610421180725 | 0.1159 | 0.1568 | 0.3859 | 1.0000000000000002e-07 --- # Framework Versions - **Transformers**: 4.41.0 - **Pytorch**: 2.5.0+cu124 - **Datasets**: 3.0.2 - **Tokenizers**: 0.19.1