End of training

README.md

@@ -0,0 +1,191 @@
+---
+license: apache-2.0
+base_model: microsoft/resnet-50
+tags:
+- generated_from_trainer
+datasets:
+- stanford-dogs
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: microsoft-resnet-50-batch32-lr0.005-standford-dogs
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: stanford-dogs
+      type: stanford-dogs
+      config: default
+      split: full
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.82555879494655
+    - name: F1
+      type: f1
+      value: 0.8098053489000772
+    - name: Precision
+      type: precision
+      value: 0.8426096100022951
+    - name: Recall
+      type: recall
+      value: 0.817750070550628
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# microsoft-resnet-50-batch32-lr0.005-standford-dogs
+
+This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the stanford-dogs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1192
+- Accuracy: 0.8256
+- F1: 0.8098
+- Precision: 0.8426
+- Recall: 0.8178
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 4.7839        | 0.0777 | 10   | 4.7747          | 0.2556   | 0.2410 | 0.4479    | 0.2436 |
+| 4.7731        | 0.1553 | 20   | 4.7576          | 0.3511   | 0.3282 | 0.6032    | 0.3338 |
+| 4.7617        | 0.2330 | 30   | 4.7363          | 0.4184   | 0.3974 | 0.6668    | 0.3947 |
+| 4.7445        | 0.3107 | 40   | 4.7115          | 0.5265   | 0.4927 | 0.7032    | 0.4993 |
+| 4.7266        | 0.3883 | 50   | 4.6846          | 0.5561   | 0.5413 | 0.7422    | 0.5333 |
+| 4.7081        | 0.4660 | 60   | 4.6547          | 0.6062   | 0.5767 | 0.7392    | 0.5828 |
+| 4.6807        | 0.5437 | 70   | 4.6161          | 0.5909   | 0.5750 | 0.7740    | 0.5673 |
+| 4.6572        | 0.6214 | 80   | 4.5761          | 0.6324   | 0.6162 | 0.8021    | 0.6102 |
+| 4.6286        | 0.6990 | 90   | 4.5274          | 0.6297   | 0.6241 | 0.8188    | 0.6080 |
+| 4.598         | 0.7767 | 100  | 4.4746          | 0.6569   | 0.6609 | 0.8380    | 0.6370 |
+| 4.5578        | 0.8544 | 110  | 4.4193          | 0.6674   | 0.6713 | 0.8301    | 0.6486 |
+| 4.521         | 0.9320 | 120  | 4.3553          | 0.6914   | 0.6868 | 0.8215    | 0.6729 |
+| 4.4888        | 1.0097 | 130  | 4.2924          | 0.7082   | 0.7064 | 0.8415    | 0.6904 |
+| 4.4312        | 1.0874 | 140  | 4.2125          | 0.7155   | 0.7076 | 0.8381    | 0.6980 |
+| 4.3865        | 1.1650 | 150  | 4.1433          | 0.7145   | 0.7115 | 0.8315    | 0.6984 |
+| 4.336         | 1.2427 | 160  | 4.0630          | 0.7082   | 0.7010 | 0.8353    | 0.6930 |
+| 4.2903        | 1.3204 | 170  | 3.9781          | 0.7148   | 0.7024 | 0.8109    | 0.6982 |
+| 4.2465        | 1.3981 | 180  | 3.8896          | 0.7376   | 0.7234 | 0.8328    | 0.7217 |
+| 4.1924        | 1.4757 | 190  | 3.8117          | 0.7476   | 0.7310 | 0.8161    | 0.7322 |
+| 4.1217        | 1.5534 | 200  | 3.7499          | 0.7510   | 0.7344 | 0.8105    | 0.7372 |
+| 4.068         | 1.6311 | 210  | 3.6340          | 0.7551   | 0.7355 | 0.8183    | 0.7409 |
+| 4.0148        | 1.7087 | 220  | 3.5678          | 0.7546   | 0.7358 | 0.8066    | 0.7413 |
+| 3.9682        | 1.7864 | 230  | 3.4852          | 0.7663   | 0.7477 | 0.8145    | 0.7530 |
+| 3.9196        | 1.8641 | 240  | 3.3841          | 0.7648   | 0.7464 | 0.8075    | 0.7520 |
+| 3.8481        | 1.9417 | 250  | 3.3003          | 0.7626   | 0.7421 | 0.8056    | 0.7495 |
+| 3.8017        | 2.0194 | 260  | 3.2395          | 0.7578   | 0.7370 | 0.8045    | 0.7461 |
+| 3.7528        | 2.0971 | 270  | 3.1183          | 0.7578   | 0.7349 | 0.8007    | 0.7457 |
+| 3.6614        | 2.1748 | 280  | 3.0364          | 0.7655   | 0.7435 | 0.8011    | 0.7531 |
+| 3.6522        | 2.2524 | 290  | 2.9775          | 0.7629   | 0.7415 | 0.7990    | 0.7507 |
+| 3.5922        | 2.3301 | 300  | 2.8995          | 0.7665   | 0.7466 | 0.8090    | 0.7551 |
+| 3.519         | 2.4078 | 310  | 2.8049          | 0.7680   | 0.7488 | 0.8129    | 0.7566 |
+| 3.4724        | 2.4854 | 320  | 2.7425          | 0.7704   | 0.7528 | 0.8170    | 0.7601 |
+| 3.4333        | 2.5631 | 330  | 2.6444          | 0.7755   | 0.7560 | 0.8236    | 0.7648 |
+| 3.4303        | 2.6408 | 340  | 2.5672          | 0.7687   | 0.7473 | 0.8178    | 0.7585 |
+| 3.3287        | 2.7184 | 350  | 2.5194          | 0.7806   | 0.7599 | 0.8229    | 0.7712 |
+| 3.2916        | 2.7961 | 360  | 2.4733          | 0.7796   | 0.7575 | 0.8223    | 0.7698 |
+| 3.1999        | 2.8738 | 370  | 2.4098          | 0.7792   | 0.7565 | 0.8158    | 0.7692 |
+| 3.211         | 2.9515 | 380  | 2.3081          | 0.7796   | 0.7571 | 0.8284    | 0.7692 |
+| 3.1437        | 3.0291 | 390  | 2.2523          | 0.7830   | 0.7600 | 0.8212    | 0.7730 |
+| 3.1036        | 3.1068 | 400  | 2.2000          | 0.7847   | 0.7619 | 0.8210    | 0.7740 |
+| 3.0345        | 3.1845 | 410  | 2.1385          | 0.7833   | 0.7606 | 0.8261    | 0.7726 |
+| 2.99          | 3.2621 | 420  | 2.1079          | 0.7799   | 0.7560 | 0.8199    | 0.7698 |
+| 2.9386        | 3.3398 | 430  | 2.0585          | 0.7821   | 0.7584 | 0.8232    | 0.7716 |
+| 2.9093        | 3.4175 | 440  | 2.0176          | 0.7823   | 0.7586 | 0.8225    | 0.7721 |
+| 2.8868        | 3.4951 | 450  | 1.9702          | 0.7818   | 0.7585 | 0.8183    | 0.7720 |
+| 2.8603        | 3.5728 | 460  | 1.8973          | 0.7864   | 0.7645 | 0.8241    | 0.7767 |
+| 2.8232        | 3.6505 | 470  | 1.8814          | 0.7855   | 0.7616 | 0.8128    | 0.7758 |
+| 2.7889        | 3.7282 | 480  | 1.8170          | 0.7886   | 0.7676 | 0.8214    | 0.7792 |
+| 2.7561        | 3.8058 | 490  | 1.7750          | 0.7920   | 0.7721 | 0.8364    | 0.7828 |
+| 2.7243        | 3.8835 | 500  | 1.7369          | 0.7906   | 0.7695 | 0.8295    | 0.7813 |
+| 2.6619        | 3.9612 | 510  | 1.7225          | 0.7971   | 0.7766 | 0.8292    | 0.7884 |
+| 2.7054        | 4.0388 | 520  | 1.6453          | 0.7983   | 0.7788 | 0.8346    | 0.7894 |
+| 2.6069        | 4.1165 | 530  | 1.6340          | 0.8000   | 0.7807 | 0.8347    | 0.7910 |
+| 2.5627        | 4.1942 | 540  | 1.6538          | 0.7971   | 0.7760 | 0.8337    | 0.7878 |
+| 2.5555        | 4.2718 | 550  | 1.5779          | 0.7998   | 0.7785 | 0.8324    | 0.7906 |
+| 2.5541        | 4.3495 | 560  | 1.5960          | 0.7945   | 0.7736 | 0.8329    | 0.7850 |
+| 2.513         | 4.4272 | 570  | 1.5537          | 0.8025   | 0.7841 | 0.8368    | 0.7941 |
+| 2.442         | 4.5049 | 580  | 1.5196          | 0.8034   | 0.7858 | 0.8380    | 0.7954 |
+| 2.4763        | 4.5825 | 590  | 1.5009          | 0.8052   | 0.7870 | 0.8345    | 0.7965 |
+| 2.4412        | 4.6602 | 600  | 1.4760          | 0.8098   | 0.7924 | 0.8391    | 0.8015 |
+| 2.383         | 4.7379 | 610  | 1.4403          | 0.8088   | 0.7920 | 0.8395    | 0.8007 |
+| 2.3731        | 4.8155 | 620  | 1.4123          | 0.8120   | 0.7956 | 0.8401    | 0.8039 |
+| 2.3616        | 4.8932 | 630  | 1.4193          | 0.8105   | 0.7940 | 0.8369    | 0.8021 |
+| 2.3311        | 4.9709 | 640  | 1.4220          | 0.8098   | 0.7934 | 0.8370    | 0.8016 |
+| 2.3373        | 5.0485 | 650  | 1.3956          | 0.8081   | 0.7907 | 0.8367    | 0.7996 |
+| 2.2879        | 5.1262 | 660  | 1.3375          | 0.8144   | 0.7976 | 0.8410    | 0.8062 |
+| 2.299         | 5.2039 | 670  | 1.3431          | 0.8146   | 0.7967 | 0.8371    | 0.8061 |
+| 2.2471        | 5.2816 | 680  | 1.3360          | 0.8151   | 0.7985 | 0.8389    | 0.8070 |
+| 2.2419        | 5.3592 | 690  | 1.3139          | 0.8139   | 0.7977 | 0.8377    | 0.8058 |
+| 2.2195        | 5.4369 | 700  | 1.3225          | 0.8151   | 0.7974 | 0.8395    | 0.8062 |
+| 2.1901        | 5.5146 | 710  | 1.2797          | 0.8173   | 0.8001 | 0.8397    | 0.8087 |
+| 2.1931        | 5.5922 | 720  | 1.2543          | 0.8192   | 0.8032 | 0.8423    | 0.8109 |
+| 2.195         | 5.6699 | 730  | 1.2767          | 0.8209   | 0.8039 | 0.8405    | 0.8125 |
+| 2.1413        | 5.7476 | 740  | 1.2735          | 0.8212   | 0.8053 | 0.8416    | 0.8132 |
+| 2.1696        | 5.8252 | 750  | 1.2694          | 0.8149   | 0.7983 | 0.8358    | 0.8069 |
+| 2.1387        | 5.9029 | 760  | 1.2532          | 0.8217   | 0.8062 | 0.8422    | 0.8136 |
+| 2.1811        | 5.9806 | 770  | 1.2426          | 0.8197   | 0.8034 | 0.8417    | 0.8116 |
+| 2.077         | 6.0583 | 780  | 1.2101          | 0.8243   | 0.8078 | 0.8464    | 0.8159 |
+| 2.1099        | 6.1359 | 790  | 1.1947          | 0.8265   | 0.8108 | 0.8455    | 0.8186 |
+| 2.0825        | 6.2136 | 800  | 1.1826          | 0.8241   | 0.8080 | 0.8455    | 0.8161 |
+| 2.0933        | 6.2913 | 810  | 1.1934          | 0.8282   | 0.8128 | 0.8474    | 0.8207 |
+| 2.0857        | 6.3689 | 820  | 1.1897          | 0.8258   | 0.8099 | 0.8465    | 0.8181 |
+| 2.0881        | 6.4466 | 830  | 1.1666          | 0.8277   | 0.8124 | 0.8477    | 0.8199 |
+| 2.074         | 6.5243 | 840  | 1.1815          | 0.8248   | 0.8081 | 0.8433    | 0.8167 |
+| 2.0145        | 6.6019 | 850  | 1.1680          | 0.8292   | 0.8130 | 0.8473    | 0.8209 |
+| 2.0778        | 6.6796 | 860  | 1.1565          | 0.8260   | 0.8094 | 0.8348    | 0.8178 |
+| 1.9784        | 6.7573 | 870  | 1.1571          | 0.8345   | 0.8201 | 0.8529    | 0.8269 |
+| 2.0595        | 6.8350 | 880  | 1.1554          | 0.8309   | 0.8165 | 0.8475    | 0.8234 |
+| 2.0252        | 6.9126 | 890  | 1.1444          | 0.8282   | 0.8140 | 0.8476    | 0.8209 |
+| 1.9708        | 6.9903 | 900  | 1.1478          | 0.8302   | 0.8158 | 0.8472    | 0.8224 |
+| 2.0656        | 7.0680 | 910  | 1.1285          | 0.8324   | 0.8169 | 0.8485    | 0.8245 |
+| 2.0086        | 7.1456 | 920  | 1.1289          | 0.8290   | 0.8148 | 0.8444    | 0.8219 |
+| 2.0056        | 7.2233 | 930  | 1.1268          | 0.8280   | 0.8130 | 0.8470    | 0.8208 |
+| 1.9498        | 7.3010 | 940  | 1.1246          | 0.8311   | 0.8158 | 0.8497    | 0.8234 |
+| 2.0067        | 7.3786 | 950  | 1.1495          | 0.8285   | 0.8132 | 0.8440    | 0.8207 |
+| 2.0171        | 7.4563 | 960  | 1.1168          | 0.8285   | 0.8138 | 0.8501    | 0.8209 |
+| 1.9683        | 7.5340 | 970  | 1.1290          | 0.8314   | 0.8165 | 0.8500    | 0.8235 |
+| 1.9771        | 7.6117 | 980  | 1.0982          | 0.8314   | 0.8153 | 0.8454    | 0.8233 |
+| 2.0086        | 7.6893 | 990  | 1.1275          | 0.8294   | 0.8151 | 0.8491    | 0.8218 |
+| 1.9854        | 7.7670 | 1000 | 1.1192          | 0.8256   | 0.8098 | 0.8426    | 0.8178 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,285 @@
+{
+  "_name_or_path": "microsoft/resnet-50",
+  "architectures": [
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_bottleneck": false,
+  "downsample_in_first_stage": false,
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
+  ],
+  "id2label": {
+    "0": "Affenpinscher",
+    "1": "Afghan Hound",
+    "2": "African Hunting Dog",
+    "3": "Airedale",
+    "4": "American Staffordshire Terrier",
+    "5": "Appenzeller",
+    "6": "Australian Terrier",
+    "7": "Basenji",
+    "8": "Basset",
+    "9": "Beagle",
+    "10": "Bedlington Terrier",
+    "11": "Bernese Mountain Dog",
+    "12": "Black And Tan Coonhound",
+    "13": "Blenheim Spaniel",
+    "14": "Bloodhound",
+    "15": "Bluetick",
+    "16": "Border Collie",
+    "17": "Border Terrier",
+    "18": "Borzoi",
+    "19": "Boston Bull",
+    "20": "Bouvier Des Flandres",
+    "21": "Boxer",
+    "22": "Brabancon Griffon",
+    "23": "Briard",
+    "24": "Brittany Spaniel",
+    "25": "Bull Mastiff",
+    "26": "Cairn",
+    "27": "Cardigan",
+    "28": "Chesapeake Bay Retriever",
+    "29": "Chihuahua",
+    "30": "Chow",
+    "31": "Clumber",
+    "32": "Cocker Spaniel",
+    "33": "Collie",
+    "34": "Curly Coated Retriever",
+    "35": "Dandie Dinmont",
+    "36": "Dhole",
+    "37": "Dingo",
+    "38": "Doberman",
+    "39": "English Foxhound",
+    "40": "English Setter",
+    "41": "English Springer",
+    "42": "Entlebucher",
+    "43": "Eskimo Dog",
+    "44": "Flat Coated Retriever",
+    "45": "French Bulldog",
+    "46": "German Shepherd",
+    "47": "German Short Haired Pointer",
+    "48": "Giant Schnauzer",
+    "49": "Golden Retriever",
+    "50": "Gordon Setter",
+    "51": "Great Dane",
+    "52": "Great Pyrenees",
+    "53": "Greater Swiss Mountain Dog",
+    "54": "Groenendael",
+    "55": "Ibizan Hound",
+    "56": "Irish Setter",
+    "57": "Irish Terrier",
+    "58": "Irish Water Spaniel",
+    "59": "Irish Wolfhound",
+    "60": "Italian Greyhound",
+    "61": "Japanese Spaniel",
+    "62": "Keeshond",
+    "63": "Kelpie",
+    "64": "Kerry Blue Terrier",
+    "65": "Komondor",
+    "66": "Kuvasz",
+    "67": "Labrador Retriever",
+    "68": "Lakeland Terrier",
+    "69": "Leonberg",
+    "70": "Lhasa",
+    "71": "Malamute",
+    "72": "Malinois",
+    "73": "Maltese Dog",
+    "74": "Mexican Hairless",
+    "75": "Miniature Pinscher",
+    "76": "Miniature Poodle",
+    "77": "Miniature Schnauzer",
+    "78": "Newfoundland",
+    "79": "Norfolk Terrier",
+    "80": "Norwegian Elkhound",
+    "81": "Norwich Terrier",
+    "82": "Old English Sheepdog",
+    "83": "Otterhound",
+    "84": "Papillon",
+    "85": "Pekinese",
+    "86": "Pembroke",
+    "87": "Pomeranian",
+    "88": "Pug",
+    "89": "Redbone",
+    "90": "Rhodesian Ridgeback",
+    "91": "Rottweiler",
+    "92": "Saint Bernard",
+    "93": "Saluki",
+    "94": "Samoyed",
+    "95": "Schipperke",
+    "96": "Scotch Terrier",
+    "97": "Scottish Deerhound",
+    "98": "Sealyham Terrier",
+    "99": "Shetland Sheepdog",
+    "100": "Shih Tzu",
+    "101": "Siberian Husky",
+    "102": "Silky Terrier",
+    "103": "Soft Coated Wheaten Terrier",
+    "104": "Staffordshire Bullterrier",
+    "105": "Standard Poodle",
+    "106": "Standard Schnauzer",
+    "107": "Sussex Spaniel",
+    "108": "Tibetan Mastiff",
+    "109": "Tibetan Terrier",
+    "110": "Toy Poodle",
+    "111": "Toy Terrier",
+    "112": "Vizsla",
+    "113": "Walker Hound",
+    "114": "Weimaraner",
+    "115": "Welsh Springer Spaniel",
+    "116": "West Highland White Terrier",
+    "117": "Whippet",
+    "118": "Wire Haired Fox Terrier",
+    "119": "Yorkshire Terrier"
+  },
+  "label2id": {
+    "Affenpinscher": 0,
+    "Afghan Hound": 1,
+    "African Hunting Dog": 2,
+    "Airedale": 3,
+    "American Staffordshire Terrier": 4,
+    "Appenzeller": 5,
+    "Australian Terrier": 6,
+    "Basenji": 7,
+    "Basset": 8,
+    "Beagle": 9,
+    "Bedlington Terrier": 10,
+    "Bernese Mountain Dog": 11,
+    "Black And Tan Coonhound": 12,
+    "Blenheim Spaniel": 13,
+    "Bloodhound": 14,
+    "Bluetick": 15,
+    "Border Collie": 16,
+    "Border Terrier": 17,
+    "Borzoi": 18,
+    "Boston Bull": 19,
+    "Bouvier Des Flandres": 20,
+    "Boxer": 21,
+    "Brabancon Griffon": 22,
+    "Briard": 23,
+    "Brittany Spaniel": 24,
+    "Bull Mastiff": 25,
+    "Cairn": 26,
+    "Cardigan": 27,
+    "Chesapeake Bay Retriever": 28,
+    "Chihuahua": 29,
+    "Chow": 30,
+    "Clumber": 31,
+    "Cocker Spaniel": 32,
+    "Collie": 33,
+    "Curly Coated Retriever": 34,
+    "Dandie Dinmont": 35,
+    "Dhole": 36,
+    "Dingo": 37,
+    "Doberman": 38,
+    "English Foxhound": 39,
+    "English Setter": 40,
+    "English Springer": 41,
+    "Entlebucher": 42,
+    "Eskimo Dog": 43,
+    "Flat Coated Retriever": 44,
+    "French Bulldog": 45,
+    "German Shepherd": 46,
+    "German Short Haired Pointer": 47,
+    "Giant Schnauzer": 48,
+    "Golden Retriever": 49,
+    "Gordon Setter": 50,
+    "Great Dane": 51,
+    "Great Pyrenees": 52,
+    "Greater Swiss Mountain Dog": 53,
+    "Groenendael": 54,
+    "Ibizan Hound": 55,
+    "Irish Setter": 56,
+    "Irish Terrier": 57,
+    "Irish Water Spaniel": 58,
+    "Irish Wolfhound": 59,
+    "Italian Greyhound": 60,
+    "Japanese Spaniel": 61,
+    "Keeshond": 62,
+    "Kelpie": 63,
+    "Kerry Blue Terrier": 64,
+    "Komondor": 65,
+    "Kuvasz": 66,
+    "Labrador Retriever": 67,
+    "Lakeland Terrier": 68,
+    "Leonberg": 69,
+    "Lhasa": 70,
+    "Malamute": 71,
+    "Malinois": 72,
+    "Maltese Dog": 73,
+    "Mexican Hairless": 74,
+    "Miniature Pinscher": 75,
+    "Miniature Poodle": 76,
+    "Miniature Schnauzer": 77,
+    "Newfoundland": 78,
+    "Norfolk Terrier": 79,
+    "Norwegian Elkhound": 80,
+    "Norwich Terrier": 81,
+    "Old English Sheepdog": 82,
+    "Otterhound": 83,
+    "Papillon": 84,
+    "Pekinese": 85,
+    "Pembroke": 86,
+    "Pomeranian": 87,
+    "Pug": 88,
+    "Redbone": 89,
+    "Rhodesian Ridgeback": 90,
+    "Rottweiler": 91,
+    "Saint Bernard": 92,
+    "Saluki": 93,
+    "Samoyed": 94,
+    "Schipperke": 95,
+    "Scotch Terrier": 96,
+    "Scottish Deerhound": 97,
+    "Sealyham Terrier": 98,
+    "Shetland Sheepdog": 99,
+    "Shih Tzu": 100,
+    "Siberian Husky": 101,
+    "Silky Terrier": 102,
+    "Soft Coated Wheaten Terrier": 103,
+    "Staffordshire Bullterrier": 104,
+    "Standard Poodle": 105,
+    "Standard Schnauzer": 106,
+    "Sussex Spaniel": 107,
+    "Tibetan Mastiff": 108,
+    "Tibetan Terrier": 109,
+    "Toy Poodle": 110,
+    "Toy Terrier": 111,
+    "Vizsla": 112,
+    "Walker Hound": 113,
+    "Weimaraner": 114,
+    "Welsh Springer Spaniel": 115,
+    "West Highland White Terrier": 116,
+    "Whippet": 117,
+    "Wire Haired Fox Terrier": 118,
+    "Yorkshire Terrier": 119
+  },
+  "layer_type": "bottleneck",
+  "model_type": "resnet",
+  "num_channels": 3,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "problem_type": "single_label_classification",
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2"
+}

config.toml

@@ -0,0 +1,27 @@
+[training_args]
+output_dir="/Users/andrewmayes/Openclassroom/CanineNet/code/"
+evaluation_strategy="steps"
+save_strategy="steps"
+learning_rate=5e-5
+#per_device_train_batch_size=32 # 512
+#per_device_eval_batch_size=32 # 512
+# num_train_epochs=5,
+eval_delay=0 # 50
+eval_steps=0.01
+#eval_accumulation_steps
+gradient_accumulation_steps=4
+gradient_checkpointing=false#true
+optim="adafactor"
+max_steps=1000 # 100
+#logging_dir=""
+#log_level="error"
+load_best_model_at_end=true
+metric_for_best_model="f1"
+greater_is_better=true
+#use_mps_device=true
+logging_steps=0.01
+save_steps=0.01
+#auto_find_batch_size=true
+report_to="mlflow"
+save_total_limit=2
+#hub_model_id="amaye15/SwinV2-Base-Document-Classifier"

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a149ec7944715556aec826546223b954ad2fb4f192f2a211384b753f192142
+size 95270232

preprocessor_config.json

@@ -0,0 +1,37 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "crop_pct",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "crop_pct": 0.875,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ConvNextImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

train.ipynb

@@ -0,0 +1,470 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Install"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: uv in /Users/andrewmayes/Openclassroom/CanineNet/env/lib/python3.12/site-packages (0.1.42)\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install uv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[2mAudited \u001b[1m12 packages\u001b[0m in 15ms\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "!uv pip install dagshub setuptools accelerate toml torch torchvision transformers mlflow datasets ipywidgets python-dotenv evaluate"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Initialized MLflow to track repo <span style=\"color: #008000; text-decoration-color: #008000\">\"amaye15/CanineNet\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "Initialized MLflow to track repo \u001b[32m\"amaye15/CanineNet\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Repository amaye15/CanineNet initialized!\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "Repository amaye15/CanineNet initialized!\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import toml\n",
+    "import torch\n",
+    "import mlflow\n",
+    "import dagshub\n",
+    "import datasets\n",
+    "import evaluate\n",
+    "from dotenv import load_dotenv\n",
+    "from torchvision.transforms import v2\n",
+    "from transformers import AutoImageProcessor, AutoModelForImageClassification, TrainingArguments, Trainer\n",
+    "\n",
+    "ENV_PATH = \"/Users/andrewmayes/Openclassroom/CanineNet/.env\"\n",
+    "CONFIG_PATH = \"/Users/andrewmayes/Openclassroom/CanineNet/code/config.toml\"\n",
+    "CONFIG = toml.load(CONFIG_PATH)\n",
+    "\n",
+    "load_dotenv(ENV_PATH)\n",
+    "\n",
+    "dagshub.init(repo_name=os.environ['MLFLOW_TRACKING_PROJECTNAME'], repo_owner=os.environ['MLFLOW_TRACKING_USERNAME'], mlflow=True, dvc=True)\n",
+    "\n",
+    "os.environ['MLFLOW_TRACKING_USERNAME'] = \"amaye15\"\n",
+    "\n",
+    "mlflow.set_tracking_uri(f'https://dagshub.com/' + os.environ['MLFLOW_TRACKING_USERNAME']\n",
+    "                         + '/' + os.environ['MLFLOW_TRACKING_PROJECTNAME'] + '.mlflow')\n",
+    "\n",
+    "CREATE_DATASET = True\n",
+    "ORIGINAL_DATASET = \"Alanox/stanford-dogs\"\n",
+    "MODIFIED_DATASET = \"amaye15/stanford-dogs\"\n",
+    "REMOVE_COLUMNS = [\"name\", \"annotations\"]\n",
+    "RENAME_COLUMNS = {\"image\":\"pixel_values\", \"target\":\"label\"}\n",
+    "SPLIT = 0.2\n",
+    "\n",
+    "METRICS = [\"accuracy\", \"f1\", \"precision\", \"recall\"]\n",
+    "# MODELS = 'google/vit-base-patch16-224'\n",
+    "# MODELS = \"google/siglip-base-patch16-224\"\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Affenpinscher: 0\n",
+      "Afghan Hound: 1\n",
+      "African Hunting Dog: 2\n",
+      "Airedale: 3\n",
+      "American Staffordshire Terrier: 4\n",
+      "Appenzeller: 5\n",
+      "Australian Terrier: 6\n",
+      "Basenji: 7\n",
+      "Basset: 8\n",
+      "Beagle: 9\n",
+      "Bedlington Terrier: 10\n",
+      "Bernese Mountain Dog: 11\n",
+      "Black And Tan Coonhound: 12\n",
+      "Blenheim Spaniel: 13\n",
+      "Bloodhound: 14\n",
+      "Bluetick: 15\n",
+      "Border Collie: 16\n",
+      "Border Terrier: 17\n",
+      "Borzoi: 18\n",
+      "Boston Bull: 19\n",
+      "Bouvier Des Flandres: 20\n",
+      "Boxer: 21\n",
+      "Brabancon Griffon: 22\n",
+      "Briard: 23\n",
+      "Brittany Spaniel: 24\n",
+      "Bull Mastiff: 25\n",
+      "Cairn: 26\n",
+      "Cardigan: 27\n",
+      "Chesapeake Bay Retriever: 28\n",
+      "Chihuahua: 29\n",
+      "Chow: 30\n",
+      "Clumber: 31\n",
+      "Cocker Spaniel: 32\n",
+      "Collie: 33\n",
+      "Curly Coated Retriever: 34\n",
+      "Dandie Dinmont: 35\n",
+      "Dhole: 36\n",
+      "Dingo: 37\n",
+      "Doberman: 38\n",
+      "English Foxhound: 39\n",
+      "English Setter: 40\n",
+      "English Springer: 41\n",
+      "Entlebucher: 42\n",
+      "Eskimo Dog: 43\n",
+      "Flat Coated Retriever: 44\n",
+      "French Bulldog: 45\n",
+      "German Shepherd: 46\n",
+      "German Short Haired Pointer: 47\n",
+      "Giant Schnauzer: 48\n",
+      "Golden Retriever: 49\n",
+      "Gordon Setter: 50\n",
+      "Great Dane: 51\n",
+      "Great Pyrenees: 52\n",
+      "Greater Swiss Mountain Dog: 53\n",
+      "Groenendael: 54\n",
+      "Ibizan Hound: 55\n",
+      "Irish Setter: 56\n",
+      "Irish Terrier: 57\n",
+      "Irish Water Spaniel: 58\n",
+      "Irish Wolfhound: 59\n",
+      "Italian Greyhound: 60\n",
+      "Japanese Spaniel: 61\n",
+      "Keeshond: 62\n",
+      "Kelpie: 63\n",
+      "Kerry Blue Terrier: 64\n",
+      "Komondor: 65\n",
+      "Kuvasz: 66\n",
+      "Labrador Retriever: 67\n",
+      "Lakeland Terrier: 68\n",
+      "Leonberg: 69\n",
+      "Lhasa: 70\n",
+      "Malamute: 71\n",
+      "Malinois: 72\n",
+      "Maltese Dog: 73\n",
+      "Mexican Hairless: 74\n",
+      "Miniature Pinscher: 75\n",
+      "Miniature Poodle: 76\n",
+      "Miniature Schnauzer: 77\n",
+      "Newfoundland: 78\n",
+      "Norfolk Terrier: 79\n",
+      "Norwegian Elkhound: 80\n",
+      "Norwich Terrier: 81\n",
+      "Old English Sheepdog: 82\n",
+      "Otterhound: 83\n",
+      "Papillon: 84\n",
+      "Pekinese: 85\n",
+      "Pembroke: 86\n",
+      "Pomeranian: 87\n",
+      "Pug: 88\n",
+      "Redbone: 89\n",
+      "Rhodesian Ridgeback: 90\n",
+      "Rottweiler: 91\n",
+      "Saint Bernard: 92\n",
+      "Saluki: 93\n",
+      "Samoyed: 94\n",
+      "Schipperke: 95\n",
+      "Scotch Terrier: 96\n",
+      "Scottish Deerhound: 97\n",
+      "Sealyham Terrier: 98\n",
+      "Shetland Sheepdog: 99\n",
+      "Shih Tzu: 100\n",
+      "Siberian Husky: 101\n",
+      "Silky Terrier: 102\n",
+      "Soft Coated Wheaten Terrier: 103\n",
+      "Staffordshire Bullterrier: 104\n",
+      "Standard Poodle: 105\n",
+      "Standard Schnauzer: 106\n",
+      "Sussex Spaniel: 107\n",
+      "Tibetan Mastiff: 108\n",
+      "Tibetan Terrier: 109\n",
+      "Toy Poodle: 110\n",
+      "Toy Terrier: 111\n",
+      "Vizsla: 112\n",
+      "Walker Hound: 113\n",
+      "Weimaraner: 114\n",
+      "Welsh Springer Spaniel: 115\n",
+      "West Highland White Terrier: 116\n",
+      "Whippet: 117\n",
+      "Wire Haired Fox Terrier: 118\n",
+      "Yorkshire Terrier: 119\n"
+     ]
+    }
+   ],
+   "source": [
+    "if CREATE_DATASET:\n",
+    "    ds = datasets.load_dataset(ORIGINAL_DATASET, token=os.getenv(\"HF_TOKEN\"), split=\"full\", trust_remote_code=True)\n",
+    "    ds = ds.remove_columns(REMOVE_COLUMNS).rename_columns(RENAME_COLUMNS)\n",
+    "\n",
+    "    labels = ds.select_columns(\"label\").to_pandas().sort_values(\"label\").get(\"label\").unique().tolist()\n",
+    "    numbers = range(len(labels))\n",
+    "    label2int = dict(zip(labels, numbers))\n",
+    "    int2label = dict(zip(numbers, labels))\n",
+    "\n",
+    "    for key, val in label2int.items():\n",
+    "        print(f\"{key}: {val}\")\n",
+    "\n",
+    "    ds = ds.class_encode_column(\"label\")\n",
+    "    ds = ds.align_labels_with_mapping(label2int, \"label\")\n",
+    "\n",
+    "    ds = ds.train_test_split(test_size=SPLIT, stratify_by_column = \"label\")\n",
+    "    #ds.push_to_hub(MODIFIED_DATASET, token=os.getenv(\"HF_TOKEN\"))\n",
+    "\n",
+    "    CONFIG[\"label2int\"] = str(label2int)\n",
+    "    CONFIG[\"int2label\"] = str(int2label)\n",
+    "\n",
+    "    # with open(\"output.toml\", \"w\") as toml_file:\n",
+    "    #     toml.dump(toml.dumps(CONFIG), toml_file)\n",
+    "\n",
+    "    #ds = datasets.load_dataset(MODIFIED_DATASET, token=os.getenv(\"HF_TOKEN\"), trust_remote_code=True, streaming=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/andrewmayes/Openclassroom/CanineNet/env/lib/python3.12/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
+      "  warnings.warn(\n",
+      "Could not find image processor class in the image processor config or the model config. Loading based on pattern matching with the model's feature extractor configuration. Please open a PR/issue to update `preprocessor_config.json` to use `image_processor_type` instead of `feature_extractor_type`. This warning will be removed in v4.40.\n",
+      "Some weights of ResNetForImageClassification were not initialized from the model checkpoint at microsoft/resnet-50 and are newly initialized because the shapes did not match:\n",
+      "- classifier.1.bias: found shape torch.Size([1000]) in the checkpoint and torch.Size([120]) in the model instantiated\n",
+      "- classifier.1.weight: found shape torch.Size([1000, 2048]) in the checkpoint and torch.Size([120, 2048]) in the model instantiated\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
+      "max_steps is given, it will override any value given in num_train_epochs\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5d2082be56df4467893881fa27d9e334",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1000 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "metrics = {metric: evaluate.load(metric) for metric in METRICS}\n",
+    "\n",
+    "\n",
+    "# for lr in [5e-3, 5e-4, 5e-5]: # 5e-5\n",
+    "#     for batch in [64]: # 32\n",
+    "#         for model_name in [\"google/vit-base-patch16-224\", \"microsoft/swinv2-base-patch4-window16-256\", \"google/siglip-base-patch16-224\"]: # \"facebook/dinov2-base\"\n",
+    "\n",
+    "lr = 5e-3\n",
+    "batch = 32\n",
+    "model_name = \"microsoft/resnet-50\"\n",
+    "\n",
+    "image_processor = AutoImageProcessor.from_pretrained(model_name)\n",
+    "model = AutoModelForImageClassification.from_pretrained(\n",
+    "model_name,\n",
+    "num_labels=len(label2int),\n",
+    "id2label=int2label,\n",
+    "label2id=label2int,\n",
+    "ignore_mismatched_sizes=True,\n",
+    ")\n",
+    "\n",
+    "# Then, in your transformations:\n",
+    "def train_transform(examples, num_ops=10, magnitude=9, num_magnitude_bins=31):\n",
+    "\n",
+    "    transformation = v2.Compose(\n",
+    "        [\n",
+    "            v2.RandAugment(\n",
+    "                num_ops=num_ops,\n",
+    "                magnitude=magnitude,\n",
+    "                num_magnitude_bins=num_magnitude_bins,\n",
+    "            )\n",
+    "        ]\n",
+    "    )\n",
+    "    # Ensure each image has three dimensions (in this case, ensure it's RGB)\n",
+    "    examples[\"pixel_values\"] = [\n",
+    "        image.convert(\"RGB\") for image in examples[\"pixel_values\"]\n",
+    "    ]\n",
+    "    # Apply transformations\n",
+    "    examples[\"pixel_values\"] = [\n",
+    "        image_processor(transformation(image), return_tensors=\"pt\")[\n",
+    "            \"pixel_values\"\n",
+    "        ].squeeze()\n",
+    "        for image in examples[\"pixel_values\"]\n",
+    "    ]\n",
+    "    return examples\n",
+    "\n",
+    "\n",
+    "def test_transform(examples):\n",
+    "    # Ensure each image is RGB\n",
+    "    examples[\"pixel_values\"] = [\n",
+    "        image.convert(\"RGB\") for image in examples[\"pixel_values\"]\n",
+    "    ]\n",
+    "    # Apply processing\n",
+    "    examples[\"pixel_values\"] = [\n",
+    "        image_processor(image, return_tensors=\"pt\")[\"pixel_values\"].squeeze()\n",
+    "        for image in examples[\"pixel_values\"]\n",
+    "    ]\n",
+    "    return examples\n",
+    "\n",
+    "\n",
+    "def compute_metrics(eval_pred):\n",
+    "    predictions, labels = eval_pred\n",
+    "    # predictions = np.argmax(logits, axis=-1)\n",
+    "    results = {}\n",
+    "    for key, val in metrics.items():\n",
+    "        if \"accuracy\" == key:\n",
+    "            result = next(\n",
+    "                iter(val.compute(predictions=predictions, references=labels).items())\n",
+    "            )\n",
+    "        if \"accuracy\" != key:\n",
+    "            result = next(\n",
+    "                iter(\n",
+    "                    val.compute(\n",
+    "                        predictions=predictions, references=labels, average=\"macro\"\n",
+    "                    ).items()\n",
+    "                )\n",
+    "            )\n",
+    "        results[result[0]] = result[1]\n",
+    "    return results\n",
+    "\n",
+    "\n",
+    "def collate_fn(examples):\n",
+    "    pixel_values = torch.stack([example[\"pixel_values\"] for example in examples])\n",
+    "    labels = torch.tensor([example[\"label\"] for example in examples])\n",
+    "    return {\"pixel_values\": pixel_values, \"labels\": labels}\n",
+    "\n",
+    "\n",
+    "def preprocess_logits_for_metrics(logits, labels):\n",
+    "    \"\"\"\n",
+    "    Original Trainer may have a memory leak.\n",
+    "    This is a workaround to avoid storing too many tensors that are not needed.\n",
+    "    \"\"\"\n",
+    "    pred_ids = torch.argmax(logits, dim=-1)\n",
+    "    return pred_ids\n",
+    "\n",
+    "ds[\"train\"].set_transform(train_transform)\n",
+    "ds[\"test\"].set_transform(test_transform)\n",
+    "\n",
+    "training_args = TrainingArguments(**CONFIG[\"training_args\"])\n",
+    "training_args.per_device_train_batch_size = batch\n",
+    "training_args.per_device_eval_batch_size = batch\n",
+    "training_args.hub_model_id = f\"amaye15/{model_name.replace('/','-')}-batch{batch}-lr{lr}-standford-dogs\"\n",
+    "\n",
+    "mlflow.start_run(run_name=f\"{model_name.replace('/','-')}-batch{batch}-lr{lr}\")\n",
+    "\n",
+    "trainer = Trainer(\n",
+    "    model=model,\n",
+    "    args=training_args,\n",
+    "    train_dataset=ds[\"train\"],\n",
+    "    eval_dataset=ds[\"test\"],\n",
+    "    tokenizer=image_processor,\n",
+    "    data_collator=collate_fn,\n",
+    "    compute_metrics=compute_metrics,\n",
+    "    # callbacks=[early_stopping_callback],\n",
+    "    preprocess_logits_for_metrics=preprocess_logits_for_metrics,\n",
+    ")\n",
+    "\n",
+    "# Train the model\n",
+    "trainer.train()\n",
+    "\n",
+    "trainer.push_to_hub()\n",
+    "\n",
+    "mlflow.end_run()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "env",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d78fe7e384da50a7fd018fd0715177c5cbfbcae3417c7ce0956c33b1571350
+size 5112