Upload README.md with huggingface_hub

README.md

@@ -14,62 +14,57 @@ metrics:
 - precision
 - recall
 pipeline_tag: image-classification
-model-index:
-- name: document-moire-detector
-  results:
-  - task:
-      type: image-classification
-      name: Moiré Pattern Detection
-    metrics:
-    - type: accuracy
-      value: 0.9950
-      name: Test Accuracy
-    - type: f1
-      value: 0.9950
-      name: Test F1
 ---
 
 # Document Moiré Detection Model (V2)
 
-A fine-tuned **DeiT-small** (Vision Transformer, 22M params) model for detecting moiré patterns in document images.
+A fine-tuned **DeiT-small** Vision Transformer for detecting moiré patterns in document images.
 
 ## Model Description
 
-This model performs binary classification to detect whether a document image contains moiré patterns —
-visual artifacts that commonly occur when:
-- Photographing a screen displaying a document
-- Scanning documents at certain resolutions
-- Screen-capturing documents with resolution mismatches
+Binary classifier: detects whether a document image contains moiré artifacts
+(common from screen photography, scanning, or screen captures).
 
 **Labels:**
-- `clean` (0): No moiré patterns detected
+- `clean` (0): No moiré patterns
 - `moire` (1): Moiré patterns detected
 
-## Training
-
-- **Base model:** `facebook/deit-small-patch16-224` (22M parameters)
-- **Training data:** 8,000 samples (4,000 clean + 4,000 synthetic moiré)
-- **Source images:** [rvl-cdip document classification dataset](https://huggingface.co/datasets/hf-tuner/rvl-cdip-document-classification)
-- **Moiré generation:** 6 synthetic methods:
-  1. Resize aliasing (screen-camera simulation)
-  2. Frequency-domain pattern overlay
-  3. Multi-frequency band interference with color fringing
-  4. Screen pixel grid + capture simulation
-  5. **Subtle moiré** — low-strength single-frequency patterns (hard examples)
-  6. **Localized moiré** — partial-image patterns with gaussian mask
-- **Epochs:** 5
-- **Learning rate:** 3e-5 (cosine schedule)
-- **Effective batch size:** 64
-- **Label smoothing:** 0.05
+## V2 Improvements (over V1)
+- **Larger model:** DeiT-small (22M params) vs DeiT-tiny (5.5M)
+- **More training data:** 8,000 samples vs 6,000
+- **6 moiré methods** (added subtle + localized patterns as hard examples)
+- **Label smoothing** (0.05) for better calibration
+- **Stronger augmentation** (rotation, hue jitter)
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Base model | `facebook/deit-small-patch16-224` |
+| Parameters | 22M |
+| Training samples | 8,000 (4,000 clean + 4,000 moiré) |
+| Test samples | 800 (400 clean + 400 moiré) |
+| Epochs | 5 |
+| Learning rate | 3e-05 (cosine schedule) |
+| Effective batch size | 64 |
+| Label smoothing | 0.05 |
+
+### Moiré Generation Methods
+1. **Resize aliasing** — downscale+upscale with NEAREST interpolation + pattern overlay
+2. **Pattern overlay** — sinusoidal interference with per-channel color variation
+3. **Multi-frequency** — 2-4 patterns at different frequencies + color displacement
+4. **Screen simulation** — pixel grid + rotation + moiré overlay
+5. **Subtle moiré** — very low strength single-frequency (hard examples)
+6. **Localized moiré** — moiré in elliptical region with gaussian mask
 
 ## Performance
 
-| Metric    | Validation | Test (held-out) |
-|-----------|-----------|-----------------|
-| Accuracy  | 98.5% | 99.5% |
-| F1 Score  | 0.985 | 0.995 |
-| Precision | 98.2% | 99.3% |
-| Recall    | 98.8% | 99.7% |
+| Metric | Eval |
+|--------|------|
+| Accuracy | 0.9912 |
+| F1 Score | 0.9913 |
+| Precision | 0.9852 |
+| Recall | 0.9975 |
 
 ## Usage
 
@@ -77,13 +72,12 @@ visual artifacts that commonly occur when:
 from transformers import pipeline
 
 classifier = pipeline("image-classification", model="Jwalit/document-moire-detector")
-result = classifier("path/to/document_image.jpg")
+result = classifier("path/to/document.jpg")
 print(result)
 # [{'label': 'clean', 'score': 0.99}, {'label': 'moire', 'score': 0.01}]
 ```
 
 Or manually:
-
 ```python
 from transformers import AutoImageProcessor, AutoModelForImageClassification
 from PIL import Image
@@ -94,23 +88,13 @@ model = AutoModelForImageClassification.from_pretrained("Jwalit/document-moire-d
 
 image = Image.open("document.jpg")
 inputs = processor(image, return_tensors="pt")
-
 with torch.no_grad():
     logits = model(**inputs).logits
-    predicted_class = logits.argmax(-1).item()
-
-print(model.config.id2label[predicted_class])  # 'clean' or 'moire'
+    label = model.config.id2label[logits.argmax(-1).item()]
+print(label)  # 'clean' or 'moire'
 ```
 
-## Version History
-
-| Version | Model | Train Size | Methods | Val F1 | Test F1 |
-|---------|-------|-----------|---------|--------|---------|
-| V1 | DeiT-tiny (5.5M) | 6,000 | 4 | 0.998 | 0.995 |
-| **V2** | **DeiT-small (22M)** | **8,000** | **6** | **0.985** | **0.995** |
-
 ## Limitations
-
-- Trained on synthetic moiré patterns — may not capture all real-world moiré variations
-- Optimized for document images; performance on natural scene images may vary
-- Input images are resized to 224×224; very subtle moiré in high-resolution images may be lost
+- Trained on synthetic moiré — may not capture all real-world variations
+- Optimized for document images; natural scenes may vary
+- Input resized to 224×224; very subtle moiré in high-res images may be lost