jhoppanne/Dogs-Breed-Image-Classification-V0
110
1---2license: apache-2.03base_model: microsoft/resnet-504tags:5- generated_from_trainer6datasets:7- imagefolder8metrics:9- accuracy10model-index:11- name: Dogs-Breed-Image-Classification-V012 results:13 - task:14 name: Image Classification15 type: image-classification16 dataset:17 name: imagefolder18 type: imagefolder19 config: default20 split: train21 args: default22 metrics:23 - name: Accuracy24 type: accuracy25 value: 0.744412050534499526---27 28<!-- This model card has been generated automatically according to the information the Trainer had access to. You29should probably proofread and complete it, then remove this comment. -->30 31# Dogs-Breed-Image-Classification-V032 33This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.34It achieves the following results on the evaluation set:35- Loss: 1.821036- Accuracy: 0.744437 38## Model description39 40This model was trained using dataset from [Kaggle - Standford dogs dataset](https://www.kaggle.com/datasets/jessicali9530/stanford-dogs-dataset)41 42Quotes from the website:43The Stanford Dogs dataset contains images of 120 breeds of dogs from around the world. This dataset has been built using images and annotation from ImageNet for the task of fine-grained image categorization. It was originally collected for fine-grain image categorization, a challenging problem as certain dog breeds have near identical features or differ in colour and age.44 45citation:46Aditya Khosla, Nityananda Jayadevaprakash, Bangpeng Yao and Li Fei-Fei. Novel dataset for Fine-Grained Image Categorization. First Workshop on Fine-Grained Visual Categorization (FGVC), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011. [pdf] [poster] [BibTex]47 48Secondary:49J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei, ImageNet: A Large-Scale Hierarchical Image Database. IEEE Computer Vision and Pattern Recognition (CVPR), 2009. [pdf] [BibTex]50## Intended uses & limitations51 52This model is fined tune solely for classifiying 120 species of dogs.53 54## Training and evaluation data55 5675% training data, 25% testing data.57 58## Training procedure59 60### Training hyperparameters61 62The following hyperparameters were used during training:63- learning_rate: 5e-0564- train_batch_size: 3265- eval_batch_size: 3266- seed: 4267- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0868- lr_scheduler_type: linear69- num_epochs: 10070 71### Training results72 73| Training Loss | Epoch | Step | Validation Loss | Accuracy |74|:-------------:|:-----:|:-----:|:---------------:|:--------:|75| 13.4902 | 1.0 | 515 | 4.7822 | 0.0104 |76| 4.7159 | 2.0 | 1030 | 4.6822 | 0.0323 |77| 4.6143 | 3.0 | 1545 | 4.5940 | 0.0554 |78| 4.4855 | 4.0 | 2060 | 4.5027 | 0.0935 |79| 4.36 | 5.0 | 2575 | 4.3961 | 0.1239 |80| 4.2198 | 6.0 | 3090 | 4.3112 | 0.1528 |81| 4.0882 | 7.0 | 3605 | 4.1669 | 0.1747 |82| 3.9314 | 8.0 | 4120 | 4.0775 | 0.2021 |83| 3.7863 | 9.0 | 4635 | 3.9487 | 0.2310 |84| 3.6511 | 10.0 | 5150 | 3.9028 | 0.2466 |85| 3.5168 | 11.0 | 5665 | 3.8635 | 0.2626 |86| 3.3999 | 12.0 | 6180 | 3.7550 | 0.2767 |87| 3.3037 | 13.0 | 6695 | 3.6973 | 0.2884 |88| 3.1613 | 14.0 | 7210 | 3.6315 | 0.3037 |89| 3.0754 | 15.0 | 7725 | 3.4839 | 0.3188 |90| 2.9441 | 16.0 | 8240 | 3.4406 | 0.3302 |91| 2.8579 | 17.0 | 8755 | 3.3528 | 0.3406 |92| 2.7531 | 18.0 | 9270 | 3.3132 | 0.3472 |93| 2.6477 | 19.0 | 9785 | 3.2736 | 0.3567 |94| 2.5422 | 20.0 | 10300 | 3.1950 | 0.3756 |95| 2.4629 | 21.0 | 10815 | 3.1174 | 0.4004 |96| 2.3735 | 22.0 | 11330 | 2.9916 | 0.4225 |97| 2.2436 | 23.0 | 11845 | 2.9205 | 0.4509 |98| 2.1578 | 24.0 | 12360 | 2.9197 | 0.4689 |99| 2.0671 | 25.0 | 12875 | 2.8196 | 0.4866 |100| 1.9902 | 26.0 | 13390 | 2.7117 | 0.4961 |101| 1.8737 | 27.0 | 13905 | 2.7129 | 0.5078 |102| 1.7945 | 28.0 | 14420 | 2.6654 | 0.5143 |103| 1.7092 | 29.0 | 14935 | 2.6273 | 0.5301 |104| 1.6228 | 30.0 | 15450 | 2.5407 | 0.5454 |105| 1.5744 | 31.0 | 15965 | 2.5412 | 0.5559 |106| 1.4761 | 32.0 | 16480 | 2.4658 | 0.5658 |107| 1.4084 | 33.0 | 16995 | 2.4247 | 0.5673 |108| 1.2624 | 34.0 | 17510 | 2.3766 | 0.5758 |109| 1.2066 | 35.0 | 18025 | 2.2879 | 0.5843 |110| 1.124 | 36.0 | 18540 | 2.2039 | 0.5872 |111| 1.074 | 37.0 | 19055 | 2.2469 | 0.5965 |112| 0.9937 | 38.0 | 19570 | 2.1575 | 0.6011 |113| 0.9418 | 39.0 | 20085 | 2.0854 | 0.6122 |114| 0.8812 | 40.0 | 20600 | 1.9991 | 0.6254 |115| 0.819 | 41.0 | 21115 | 2.0161 | 0.6312 |116| 0.771 | 42.0 | 21630 | 1.9253 | 0.6375 |117| 0.7128 | 43.0 | 22145 | 1.9412 | 0.6390 |118| 0.6434 | 44.0 | 22660 | 1.8463 | 0.6509 |119| 0.6138 | 45.0 | 23175 | 1.8163 | 0.6650 |120| 0.5325 | 46.0 | 23690 | 1.7881 | 0.6710 |121| 0.498 | 47.0 | 24205 | 1.7526 | 0.6744 |122| 0.4565 | 48.0 | 24720 | 1.7155 | 0.6859 |123| 0.4109 | 49.0 | 25235 | 1.6874 | 0.6946 |124| 0.3681 | 50.0 | 25750 | 1.7386 | 0.6997 |125| 0.3306 | 51.0 | 26265 | 1.6578 | 0.7104 |126| 0.2913 | 52.0 | 26780 | 1.6641 | 0.7104 |127| 0.2598 | 53.0 | 27295 | 1.6823 | 0.7162 |128| 0.2311 | 54.0 | 27810 | 1.6835 | 0.7157 |129| 0.2115 | 55.0 | 28325 | 1.6581 | 0.7206 |130| 0.1843 | 56.0 | 28840 | 1.6286 | 0.7274 |131| 0.1668 | 57.0 | 29355 | 1.6358 | 0.7225 |132| 0.1483 | 58.0 | 29870 | 1.6422 | 0.7250 |133| 0.132 | 59.0 | 30385 | 1.6618 | 0.7284 |134| 0.1164 | 60.0 | 30900 | 1.6894 | 0.7262 |135| 0.1043 | 61.0 | 31415 | 1.6923 | 0.7276 |136| 0.0937 | 62.0 | 31930 | 1.6627 | 0.7323 |137| 0.0826 | 63.0 | 32445 | 1.6280 | 0.7342 |138| 0.0743 | 64.0 | 32960 | 1.6204 | 0.7366 |139| 0.0638 | 65.0 | 33475 | 1.6890 | 0.7383 |140| 0.0603 | 66.0 | 33990 | 1.6967 | 0.7335 |141| 0.0491 | 67.0 | 34505 | 1.6975 | 0.7306 |142| 0.0459 | 68.0 | 35020 | 1.7242 | 0.7337 |143| 0.0416 | 69.0 | 35535 | 1.7019 | 0.7374 |144| 0.0382 | 70.0 | 36050 | 1.7098 | 0.7381 |145| 0.0378 | 71.0 | 36565 | 1.7188 | 0.7383 |146| 0.0326 | 72.0 | 37080 | 1.8212 | 0.7376 |147| 0.0323 | 73.0 | 37595 | 1.7965 | 0.7393 |148| 0.0299 | 74.0 | 38110 | 1.7934 | 0.7301 |149| 0.0259 | 75.0 | 38625 | 1.7799 | 0.7335 |150| 0.0276 | 76.0 | 39140 | 1.8456 | 0.7301 |151| 0.0257 | 77.0 | 39655 | 1.8551 | 0.7391 |152| 0.0234 | 78.0 | 40170 | 1.7780 | 0.7391 |153| 0.0222 | 79.0 | 40685 | 1.8216 | 0.7362 |154| 0.0195 | 80.0 | 41200 | 1.8333 | 0.7352 |155| 0.0214 | 81.0 | 41715 | 1.8526 | 0.7430 |156| 0.0207 | 82.0 | 42230 | 1.8581 | 0.7364 |157| 0.0171 | 83.0 | 42745 | 1.8329 | 0.7393 |158| 0.0175 | 84.0 | 43260 | 1.8841 | 0.7396 |159| 0.0165 | 85.0 | 43775 | 1.8381 | 0.7345 |160| 0.0152 | 86.0 | 44290 | 1.8192 | 0.7379 |161| 0.0168 | 87.0 | 44805 | 1.8538 | 0.7388 |162| 0.0158 | 88.0 | 45320 | 1.8390 | 0.7371 |163| 0.0181 | 89.0 | 45835 | 1.8555 | 0.7374 |164| 0.0142 | 90.0 | 46350 | 1.7987 | 0.7352 |165| 0.0147 | 91.0 | 46865 | 1.8446 | 0.7427 |166| 0.0142 | 92.0 | 47380 | 1.8210 | 0.7444 |167| 0.0124 | 93.0 | 47895 | 1.8233 | 0.7405 |168| 0.0128 | 94.0 | 48410 | 1.8517 | 0.7393 |169| 0.0135 | 95.0 | 48925 | 1.8408 | 0.7413 |170| 0.0122 | 96.0 | 49440 | 1.8153 | 0.7396 |171| 0.0141 | 97.0 | 49955 | 1.8645 | 0.7432 |172| 0.0121 | 98.0 | 50470 | 1.8526 | 0.7430 |173| 0.0124 | 99.0 | 50985 | 1.8693 | 0.7388 |174| 0.0113 | 100.0 | 51500 | 1.8051 | 0.7427 |175 176 177### Framework versions178 179- Transformers 4.37.2180- Pytorch 2.3.0181- Datasets 2.15.0182- Tokenizers 0.15.1183