Fix storage limit by caching to /tmp

.dockerignore

@@ -0,0 +1,25 @@
+# Ignore cache and unnecessary files
+__pycache__/
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.so
+*.egg
+*.egg-info/
+dist/
+build/
+*.log
+.git/
+.gitignore
+.DS_Store
+*.swp
+*.swo
+*~
+.vscode/
+.idea/
+*.pt
+*.pth
+*.ckpt
+*.weights
+

.gitignore

@@ -0,0 +1,41 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+.venv
+*.egg-info/
+dist/
+build/
+
+# Hugging Face cache
+.cache/
+transformers_cache/
+
+# Model weights
+*.pt
+*.pth
+*.ckpt
+*.weights
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Gradio
+flagged/
+gradio_cached_examples/
+
+# Logs
+*.log
+

DEPLOYMENT.md

@@ -0,0 +1,88 @@
+# Deployment Guide for Hugging Face Spaces
+
+## Storage Limit Error Fix
+
+If you see "Workload evicted, storage limit exceeded (50G)", here's how to fix it:
+
+### Quick Fix (Recommended)
+The pipeline now uses `/tmp` for caching (ephemeral storage), which resets on each container restart. This should prevent storage buildup.
+
+**To apply the fix:**
+1. Push the updated code to your Space
+2. The Space will rebuild automatically
+3. The model will cache to `/tmp` instead of persistent storage
+
+### Manual Cleanup
+If your Space is still stuck, you need to clean up old cached files:
+
+1. **Go to your Space settings** on Hugging Face
+2. **Factory Reboot** your Space:
+   - Settings → Factory reboot
+   - This will clear all persistent storage and restart fresh
+
+### Alternative: Upgrade Space Storage
+If you need more persistent storage:
+1. Go to Settings → Hardware
+2. Upgrade to a tier with more storage (costs $$$)
+
+## Storage Optimization Applied
+
+The following changes reduce storage usage:
+
+### 1. Cache to /tmp (ephemeral)
+```python
+# In sorghum_pipeline/segmentation/manager.py
+cache_dir = "/tmp/huggingface_cache"  # Cleared on restart
+```
+
+### 2. Low memory mode
+```python
+low_cpu_mem_usage=True  # Reduces peak memory during model load
+```
+
+### 3. Ignore files
+- `.dockerignore`: Prevents copying cache/models during build
+- `.gitignore`: Prevents committing large files
+
+### 4. Smaller model resolution
+- Using 512x512 instead of 1024x1024 for 4x speedup and less memory
+
+## Monitoring Storage
+
+To check storage usage in your Space:
+1. Open the Space logs
+2. Look for disk usage warnings
+3. If approaching 50GB, do a factory reboot
+
+## Expected Storage Usage
+
+- **BRIA RMBG-2.0 model**: ~350MB (cached to /tmp)
+- **PyTorch/Transformers libs**: ~2-3GB
+- **Application code**: <50MB
+- **Temporary files**: <1GB (cleared after each run)
+
+**Total**: ~3-4GB (well under 50GB limit)
+
+## Troubleshooting
+
+### "No space left on device"
+- Factory reboot the Space
+- Check if any large files were committed to git
+
+### "Model download failed"
+- Check HF_TOKEN is set in Space secrets
+- Verify internet connectivity in Space
+
+### Slow startup
+- First startup downloads model (~350MB)
+- Subsequent startups load from /tmp (fast)
+- After container restart, re-downloads to /tmp
+
+## Best Practices
+
+1. ✅ Use `/tmp` for all caches
+2. ✅ Enable `low_cpu_mem_usage=True`
+3. ✅ Keep `.dockerignore` and `.gitignore` updated
+4. ❌ Don't commit model weights to git
+5. ❌ Don't use persistent cache directories
+

README.md

@@ -1,12 +1,31 @@
 ---
 title: Plant Analysis Demo
-emoji: 💻
-colorFrom: indigo
+emoji: 🌿
+colorFrom: green
 colorTo: blue
 sdk: gradio
 sdk_version: 5.48.0
 app_file: app.py
 pinned: false
+python_version: 3.10
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# 🌿 Automated Plant Analysis Pipeline
+
+Analyze plant images with automated segmentation, feature extraction, and morphological analysis.
+
+## Features
+- **Multi-plant detection**: Automatically detects and analyzes multiple plants
+- **Segmentation**: BRIA RMBG-2.0 model for accurate plant segmentation
+- **Vegetation indices**: NDVI, GNDVI, SAVI with statistics
+- **Texture analysis**: LBP, HOG, Lacunarity on green band
+- **Morphology**: Height calculation for each plant, size visualization
+
+## Storage Optimization
+This app uses `/tmp` for model caching to avoid persistent storage limits on Hugging Face Spaces.
+
+## Usage
+1. Upload a plant image (TIFF, PNG, or JPG)
+2. Or select a preset image (Sorghum, Corn, Cotton)
+3. Click "Run Pipeline"
+4. Watch results appear progressively!

cleanup_cache.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+"""
+Cleanup script for Hugging Face Spaces to remove cached models and free up storage.
+Run this if you encounter storage limit errors.
+"""
+
+import os
+import shutil
+from pathlib import Path
+
+def get_size(path):
+    """Get size of directory in GB."""
+    total = 0
+    try:
+        for entry in os.scandir(path):
+            if entry.is_file(follow_symlinks=False):
+                total += entry.stat().st_size
+            elif entry.is_dir(follow_symlinks=False):
+                total += get_size(entry.path)
+    except PermissionError:
+        pass
+    return total / (1024**3)  # Convert to GB
+
+def cleanup():
+    """Remove cache directories to free up space."""
+    cache_dirs = [
+        Path.home() / ".cache" / "huggingface",
+        Path.home() / ".cache" / "torch",
+        Path("/tmp/huggingface_cache"),
+        Path("/tmp/torch_cache"),
+    ]
+    
+    total_freed = 0
+    for cache_dir in cache_dirs:
+        if cache_dir.exists():
+            size = get_size(str(cache_dir))
+            print(f"Removing {cache_dir} ({size:.2f} GB)...")
+            try:
+                shutil.rmtree(cache_dir)
+                total_freed += size
+                print(f"  ✓ Removed")
+            except Exception as e:
+                print(f"  ✗ Failed: {e}")
+    
+    print(f"\nTotal space freed: {total_freed:.2f} GB")
+
+if __name__ == "__main__":
+    cleanup()
+

sorghum_pipeline/segmentation/manager.py

@@ -29,13 +29,18 @@ class SegmentationManager:
         import os
         hf_token = os.environ.get("HF_TOKEN")
         
-        logger.info(f"Loading BRIA model: {model_name}")
+        # Set cache directory to /tmp to avoid persistent storage issues
+        if cache_dir is None:
+            cache_dir = "/tmp/huggingface_cache"
+        
+        logger.info(f"Loading BRIA model: {model_name} (cache: {cache_dir})")
         self.model = AutoModelForImageSegmentation.from_pretrained(
             model_name,
             trust_remote_code=trust_remote_code,
-            cache_dir=cache_dir if cache_dir else None,
+            cache_dir=cache_dir,
             local_files_only=local_files_only,
             token=hf_token,
+            low_cpu_mem_usage=True,  # Reduce memory usage during loading
         ).eval().to(self.device)
         
         # Use 512x512 for 4x speed improvement