Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+
+# Aesthetic Scorer
+
+This model predicts 7 different aesthetic metrics for images:
+- Overall aesthetic score
+- Technical quality score
+- Composition score 
+- Lighting score
+- Color harmony score
+- Depth of field score
+- Content score
+
+## Model Details
+- Based on CLIP ViT-B/32 visual encoder
+- Fine-tuned on the PARA dataset
+- Returns scores between 0-5 for each aesthetic dimension
+
+## Usage
+
+```python
+from transformers import CLIPProcessor
+from aesthetic_scorer import AestheticScorer
+import torch
+from PIL import Image
+
+# Load the model
+processor = CLIPProcessor.from_pretrained("YOUR_USERNAME/aesthetic-scorer")
+model = torch.load("YOUR_USERNAME/aesthetic-scorer/model.pt")
+
+# Process an image
+image = Image.open("your_image.jpg")
+inputs = processor(images=image, return_tensors="pt")["pixel_values"]
+
+# Get scores
+with torch.no_grad():
+    scores = model(inputs)
+
+# Print results
+aesthetic_categories = ["Overall", "Quality", "Composition", "Lighting", "Color", "Depth of Field", "Content"]
+for category, score in zip(aesthetic_categories, scores):
+    print(f"{category}: {score.item():.2f}/10")
+```

aesthetic_scorer.py

@@ -0,0 +1,44 @@
+
+import torch.nn as nn
+
+class AestheticScorer(nn.Module):
+    '''
+    Fine-tuned CLIP model to predict aesthetic scores (e.g., light, depth, composition) based on the PARA dataset.
+    '''
+    def __init__(self, backbone):
+        super().__init__()
+        self.backbone = backbone
+            
+        # Define the scoring heads
+        hidden_dim = backbone.config.hidden_size
+        self.aesthetic_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.quality_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.composition_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.light_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.color_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.dof_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+        
+        self.content_head = nn.Sequential(
+            nn.Linear(hidden_dim, 1),
+        )
+    
+    def forward(self, pixel_values):
+        features = self.backbone(pixel_values).pooler_output
+        return self.aesthetic_head(features), self.quality_head(features), self.composition_head(features), self.light_head(features), self.color_head(features), self.dof_head(features), self.content_head(features)

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59853d88e95c287d101bd692c876232f5cd4a860299060d370258ad68b36042d
+size 349912662

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "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": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

requirements.txt

@@ -0,0 +1,3 @@
+torch>=1.8.0
+transformers>=4.11.0
+pillow>=8.0.0

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "CLIPProcessor",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}