robertsw/aesthetics_v1

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+base_model: facebook/dinov2-large
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: aesthetics_v2
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5580614847630554
+---
+
+<!-- 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. -->
+
+# aesthetics_v2
+
+This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6501
+- Accuracy: 0.5581
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.1465        | 0.17  | 20   | 1.6860          | 0.5313   |
+| 1.2703        | 0.34  | 40   | 1.8412          | 0.5014   |
+| 1.3152        | 0.52  | 60   | 1.8200          | 0.5042   |
+| 1.2313        | 0.69  | 80   | 1.7971          | 0.5112   |
+| 1.3476        | 0.86  | 100  | 1.7649          | 0.5100   |
+| 1.2597        | 1.03  | 120  | 1.7454          | 0.5175   |
+| 1.0094        | 1.2   | 140  | 1.7356          | 0.5257   |
+| 0.9743        | 1.37  | 160  | 1.7074          | 0.5352   |
+| 1.0209        | 1.55  | 180  | 1.7331          | 0.5322   |
+| 1.0692        | 1.72  | 200  | 1.7370          | 0.5331   |
+| 1.0556        | 1.89  | 220  | 1.6788          | 0.5487   |
+| 0.8634        | 2.06  | 240  | 1.6644          | 0.5536   |
+| 0.79          | 2.23  | 260  | 1.6848          | 0.5531   |
+| 0.7916        | 2.4   | 280  | 1.6761          | 0.5528   |
+| 0.7454        | 2.58  | 300  | 1.6520          | 0.5534   |
+| 0.7497        | 2.75  | 320  | 1.6337          | 0.5554   |
+| 0.7537        | 2.92  | 340  | 1.6501          | 0.5581   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,167 @@
+{
+  "_name_or_path": "facebook/dinov2-large",
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2ForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Indie",
+    "1": "Kawaii",
+    "10": "boho",
+    "11": "classic",
+    "12": "classiccore",
+    "13": "clean",
+    "14": "coquette",
+    "15": "corporate",
+    "16": "cottagecore",
+    "17": "cowboycore",
+    "18": "cyberpunk",
+    "19": "dark_academia",
+    "2": "VSCO",
+    "20": "e-girl",
+    "21": "europecore",
+    "22": "fairy",
+    "23": "gorpcore",
+    "24": "goth",
+    "25": "grunge",
+    "26": "it",
+    "27": "it_girl",
+    "28": "kidcore",
+    "29": "mermaidcore",
+    "3": "Y2K",
+    "30": "minimalistic",
+    "31": "mob_wife",
+    "32": "monochrome",
+    "33": "normcore",
+    "34": "office",
+    "35": "office_siren",
+    "36": "old_money",
+    "37": "pearlcore",
+    "38": "preppy",
+    "39": "punk",
+    "4": "acubi",
+    "40": "romcom",
+    "41": "royalcore",
+    "42": "softgirl",
+    "43": "stealth_wealth",
+    "44": "streetwear",
+    "45": "techwear",
+    "46": "tomato",
+    "47": "twee",
+    "48": "vanilla",
+    "49": "vintage",
+    "5": "art",
+    "50": "westerncore",
+    "6": "athleisure",
+    "7": "balletcore",
+    "8": "barbiecore",
+    "9": "bohemian"
+  },
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "label2id": {
+    "Indie": "0",
+    "Kawaii": "1",
+    "VSCO": "2",
+    "Y2K": "3",
+    "acubi": "4",
+    "art": "5",
+    "athleisure": "6",
+    "balletcore": "7",
+    "barbiecore": "8",
+    "bohemian": "9",
+    "boho": "10",
+    "classic": "11",
+    "classiccore": "12",
+    "clean": "13",
+    "coquette": "14",
+    "corporate": "15",
+    "cottagecore": "16",
+    "cowboycore": "17",
+    "cyberpunk": "18",
+    "dark_academia": "19",
+    "e-girl": "20",
+    "europecore": "21",
+    "fairy": "22",
+    "gorpcore": "23",
+    "goth": "24",
+    "grunge": "25",
+    "it": "26",
+    "it_girl": "27",
+    "kidcore": "28",
+    "mermaidcore": "29",
+    "minimalistic": "30",
+    "mob_wife": "31",
+    "monochrome": "32",
+    "normcore": "33",
+    "office": "34",
+    "office_siren": "35",
+    "old_money": "36",
+    "pearlcore": "37",
+    "preppy": "38",
+    "punk": "39",
+    "romcom": "40",
+    "royalcore": "41",
+    "softgirl": "42",
+    "stealth_wealth": "43",
+    "streetwear": "44",
+    "techwear": "45",
+    "tomato": "46",
+    "twee": "47",
+    "vanilla": "48",
+    "vintage": "49",
+    "westerncore": "50"
+  },
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_swiglu_ffn": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82b051ece02fec589140071dfe4ba01a248afd23df02c5d6138f12940326687
+size 1217944124

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f4a995195aadfbb28612acc417e19029378bc33f7fb2d5441ab349d3225531
+size 4856