Iv-1

.dockerignore

@@ -0,0 +1,29 @@
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+env/
+venv/
+pip-log.txt
+pip-delete-this-directory.txt
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.log
+.git
+.gitignore
+.mypy_cache
+.pytest_cache
+.hypothesis
+*.egg-info/
+dist/
+build/
+*.egg
+data/*.html
+data/recognition_log.csv
+app.py

Dockerfile

@@ -0,0 +1,25 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first for better caching
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY api.py .
+COPY data/ ./data/
+COPY .env .
+
+# Expose port
+EXPOSE 7860
+
+# Run the application
+CMD ["uvicorn", "api:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,11 +1,73 @@
 ---
-title: Greenai
-emoji: 🐠
+title: Mushroom Species Recognition API
+emoji: 🍄
 colorFrom: green
-colorTo: purple
+colorTo: yellow
 sdk: docker
 pinned: false
 license: mit
+app_port: 7860
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Mushroom Species Recognition API
+
+AI-powered mushroom species identification using BioCLIP and VLM models.
+
+## Features
+
+- **BioCLIP Model**: Fast species recognition from biological specimens
+- **VLM Fallback**: Nvidia Nemotron VLM for enhanced accuracy
+- **MCC Campus Database**: Location data for mushrooms found at MCC campus
+- **RESTful API**: Simple JSON-based API
+
+## API Endpoints
+
+### POST /recognize
+Upload an image to identify mushroom species.
+
+**Request:**
+```bash
+curl -X POST "https://your-space.hf.space/recognize" \
+  -F "file=@mushroom.jpg"
+```
+
+**Response:**
+```json
+{
+  "success": true,
+  "found_in_database": true,
+  "species": "Leucocoprinus birnbaumii",
+  "location": "MCC Pavilion",
+  "latitude": 12.91865,
+  "longitude": 80.1213,
+  "confidence": 0.615,
+  "identified_by": "BioCLIP",
+  "top_matches": [...]
+}
+```
+
+### GET /health
+Check API health status.
+
+### GET /
+API documentation and info.
+
+## Usage
+
+Visit `/docs` for interactive Swagger documentation.
+
+## Technology Stack
+
+- **FastAPI**: Web framework
+- **BioCLIP**: Biological image recognition
+- **OpenCLIP**: Vision-language model
+- **Nvidia Nemotron VLM**: Fallback identification via OpenRouter
+- **Docker**: Containerization
+
+## Setup
+
+Set your `OPENROUTER_API_KEY` in the Space secrets for VLM fallback functionality.
+
+## License
+
+MIT

api.py

@@ -0,0 +1,275 @@
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+import pandas as pd
+from PIL import Image
+import torch
+import numpy as np
+from datetime import datetime
+import os
+import open_clip
+import base64
+from io import BytesIO
+from dotenv import load_dotenv
+import requests
+
+# Load environment variables
+load_dotenv()
+
+THRESHOLD = 0.50
+LOG_FILE = "data/recognition_log.csv"
+# Read from environment (works with Hugging Face Spaces secrets)
+OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY", "")
+
+# Load BioCLIP model
+model, _, preprocess = open_clip.create_model_and_transforms('hf-hub:imageomics/bioclip')
+tokenizer = open_clip.get_tokenizer('hf-hub:imageomics/bioclip')
+
+# Load species database
+db = pd.read_csv("data/mushrooms.csv")
+
+# Create labels
+enhanced_labels = [species for species in db["species"]]
+labels = enhanced_labels
+labels.append("unknown species")
+
+# Initialize log file
+if not os.path.exists(LOG_FILE):
+    log_df = pd.DataFrame(columns=["timestamp", "species", "confidence", "location", "lat", "lon", "status"])
+    log_df.to_csv(LOG_FILE, index=False)
+
+# Initialize FastAPI
+app = FastAPI(title="Mushroom Recognition API", version="1.0.0")
+
+# CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+def log_recognition(species, confidence, location="N/A", lat="N/A", lon="N/A", status="success"):
+    log_entry = {
+        "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+        "species": species,
+        "confidence": confidence,
+        "location": location,
+        "lat": lat,
+        "lon": lon,
+        "status": status
+    }
+    log_df = pd.read_csv(LOG_FILE)
+    log_df = pd.concat([log_df, pd.DataFrame([log_entry])], ignore_index=True)
+    log_df.to_csv(LOG_FILE, index=False)
+
+def identify_with_vlm(image):
+    if not OPENROUTER_API_KEY:
+        return None, "OpenRouter API key not configured", False
+    
+    try:
+        buffered = BytesIO()
+        image.save(buffered, format="JPEG")
+        img_base64 = base64.b64encode(buffered.getvalue()).decode()
+        
+        species_list = "\n".join([f"- {s}" for s in db["species"].tolist()])
+        
+        response = requests.post(
+            url="https://openrouter.ai/api/v1/chat/completions",
+            headers={
+                "Authorization": f"Bearer {OPENROUTER_API_KEY}",
+                "Content-Type": "application/json"
+            },
+            json={
+                "model": "nvidia/nemotron-nano-12b-v2-vl:free",
+                "messages": [
+                    {
+                        "role": "user",
+                        "content": [
+                            {
+                                "type": "image_url",
+                                "image_url": {
+                                    "url": f"data:image/jpeg;base64,{img_base64}"
+                                }
+                            },
+                            {
+                                "type": "text",
+                                "text": f"""You are an expert mycologist. Analyze this mushroom/fungus image very carefully.
+
+Look at:
+- Cap shape, color, and texture
+- Gill structure and color
+- Stem characteristics
+- Size and proportions
+- Growing environment
+
+Match it to ONE species from this exact list (use the exact name as written):
+
+{species_list}
+
+Respond with ONLY the exact species name from the list above that best matches this mushroom. If you're not confident about any match, respond with "Unknown"."""
+                            }
+                        ]
+                    }
+                ]
+            }
+        )
+        
+        response_data = response.json()
+        
+        if "error" in response_data:
+            error_msg = response_data["error"].get("message", "Unknown API error")
+            return None, f"API Error: {error_msg}", False
+        
+        if "choices" not in response_data:
+            return None, f"Unexpected response format", False
+        
+        result = response_data["choices"][0]["message"]["content"].strip()
+        result = result.split('\n')[0].strip()
+        if '.' in result:
+            result = result.split('.')[0].strip()
+        
+        for idx, species in enumerate(db["species"]):
+            if species.lower() in result.lower() or result.lower() in species.lower():
+                return idx, species, True
+        
+        return None, result, False
+        
+    except Exception as e:
+        return None, f"Error: {str(e)}", False
+
+def recognize_species_internal(image: Image.Image):
+    # BioCLIP inference
+    image_input = preprocess(image).unsqueeze(0)
+    text_input = tokenizer(labels)
+    
+    with torch.no_grad():
+        image_features = model.encode_image(image_input)
+        text_features = model.encode_text(text_input)
+        
+        image_features /= image_features.norm(dim=-1, keepdim=True)
+        text_features /= text_features.norm(dim=-1, keepdim=True)
+        
+        scores = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+    idx = scores.argmax().item()
+    confidence = scores[0][idx].item()
+
+    # Get top 5 matches
+    top_k = min(5, len(scores[0]))
+    top_scores, top_indices = scores[0].topk(top_k)
+    top_matches = []
+    for i in range(top_k):
+        match_idx = top_indices[i].item()
+        match_score = top_scores[i].item()
+        if match_idx < len(labels) - 1:
+            top_matches.append({
+                "species": db.iloc[match_idx]['species'],
+                "confidence": round(float(match_score), 3)
+            })
+        else:
+            top_matches.append({
+                "species": "Unknown species",
+                "confidence": round(float(match_score), 3)
+            })
+
+    # Check if unknown or low confidence
+    if idx == len(labels)-1 or confidence < THRESHOLD:
+        log_recognition("Unknown", confidence, status="not_found")
+        
+        # Try VLM fallback
+        if OPENROUTER_API_KEY:
+            vlm_idx, vlm_species, found_in_db = identify_with_vlm(image)
+            
+            if vlm_idx is not None and found_in_db:
+                row = db.iloc[vlm_idx]
+                log_recognition(row['species'], 0.85, row['location'], row['lat'], row['lon'], status="vlm_success")
+                
+                return {
+                    "success": True,
+                    "found_in_database": True,
+                    "species": row['species'],
+                    "location": row['location'],
+                    "latitude": float(row['lat']),
+                    "longitude": float(row['lon']),
+                    "confidence": 0.85,
+                    "identified_by": "Nvidia Nemotron VLM",
+                    "top_matches": top_matches
+                }
+            else:
+                # Species identified but not in database
+                log_recognition(vlm_species, 0.85, status="not_at_mcc")
+                return {
+                    "success": True,
+                    "found_in_database": False,
+                    "identified_species": vlm_species,
+                    "message": "This mushroom is not available in the MCC campus database",
+                    "identified_by": "Nvidia Nemotron VLM",
+                    "top_matches": top_matches
+                }
+        
+        return {
+            "success": False,
+            "message": "Species not found in database",
+            "confidence": round(float(confidence), 3),
+            "top_matches": top_matches
+        }
+
+    # Found in database with high confidence
+    row = db.iloc[idx]
+    log_recognition(row['species'], confidence, row['location'], row['lat'], row['lon'], status="success")
+    
+    return {
+        "success": True,
+        "found_in_database": True,
+        "species": row['species'],
+        "location": row['location'],
+        "latitude": float(row['lat']),
+        "longitude": float(row['lon']),
+        "confidence": round(float(confidence), 3),
+        "identified_by": "BioCLIP",
+        "top_matches": top_matches
+    }
+
+@app.get("/")
+async def root():
+    return {
+        "message": "Mushroom Recognition API",
+        "version": "1.0.0",
+        "endpoints": {
+            "/recognize": "POST - Upload image for species recognition",
+            "/health": "GET - Health check"
+        }
+    }
+
+@app.get("/health")
+async def health():
+    return {"status": "healthy", "model_loaded": True}
+
+@app.post("/recognize")
+async def recognize(file: UploadFile = File(...)):
+    """
+    Recognize mushroom species from uploaded image
+    
+    Returns JSON with species information
+    """
+    try:
+        # Read and validate image
+        contents = await file.read()
+        image = Image.open(BytesIO(contents))
+        
+        # Convert to RGB if needed
+        if image.mode != 'RGB':
+            image = image.convert('RGB')
+        
+        # Perform recognition
+        result = recognize_species_internal(image)
+        
+        return result
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error processing image: {str(e)}")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

data/mushrooms.csv

@@ -0,0 +1,51 @@
+sno,species,location,lat,lon
+1,Agaricus trisulpurates,MCC IOB Road,12.92206,80.12306
+2,Pleurotus sp1,MCC Lake Road,12.91558,80.11692
+3,Agaricus placomyces,MCC Infirmary,12.92088,80.12301
+4,Agaricus subrufescens,MCC Barnes hall,12.9196,80.11901
+5,Chlorophyllum molybdites 1,MCC IOB Road,12.92205,80.12304
+6,Chlorophyllum rhacodes 1,MCC Pavilion Road,12.91868,80.12091
+7,Lepiota erythrosticta,MCC Botany Road,12.91946,80.12065
+8,Lepiota sp1,MCC Botany Tank,12.92052,80.12086
+9,Lepiota sp2,MCC Botany Road,12.91948,80.12075
+10,Lepiota citriodora,MCC Lake road,12.91644,80.11697
+11,Leucoagaricus rhodocephalus,MCC Botany Road,12.91968,80.12076
+12,Leucoagaricus tropicus,MCC Microbiology Dept.,12.92146,80.12112
+13,Leucocoprinus birnbaumii,MCC Pavilion,12.91865,80.1213
+14,Leucocoprinus parvipileus 1,MCC Botany Road,12.91974,80.12077
+15,Leucocoprinus rubrotinctus,MCC Botany Road,12.91978,80.12077
+16,Amanita sp1,MCC Botany Road,12.91988,80.12079
+17,Saproamanita manicata 1,MCC Botany Road,12.91986,80.12079
+18,Saproamanita aureofloccosa,MCC MacPhail,12.91937,80.12102
+19,Limacella clavocystidiata,MCC Botany Road,12.92005,80.12078
+20,Entoloma shwethum,MCC Lake road,12.91622,80.11696
+21,Entoloma sp1,MCC Lake road,12.91623,80.11696
+22,Entoloma sp2,MCC Lake road,12.91591,80.11695
+23,Entoloma sp 3,MCC Lake road,12.91582,80.11693
+24,Entoloma holmvassdalenense,MCC Lake road,12.91574,80.11691
+25,Termitomyces medius 1,MCC Thomas hall,12.92158,80.11899
+26,Termitomyces microcarpus,MCC Farm,12.91612,80.12407
+27,Termitomyces sp1,MCC Social work department,12.91618,80.12393
+28,Termitomyces heimii,MCC Thomas hall,12.92179,80.11897
+29,Termitomyces eurrhizus,MCC Botany Road,12.92055,80.12084
+30,Omphalotus olivascens,MCC Lake road,12.91566,80.11692
+31,Gymnophilus dilepis,MCC IOB Road,12.92235,80.12327
+32,Volvariella pseudovolvacea,MCC Boxing Ring,12.92089,80.12123
+33,Volvariella sp1,MCC Lake Road,12.91558,80.11691
+34,Cantharocybe gruberi,MCC Botany Tank Road,12.92031,80.12088
+35,Macrocybe sardoa,MCC Infirmary,12.92087,80.123
+36,Trogia infundibuliformis,MCC IGH road,12.91866,80.1205
+37,Dermoloma sp1,MCC Botany Road,12.92024,80.12088
+38,Tetrapyrgos nigripes,MCC Farm,12.91613,80.12424
+39,Lactocollybia epia,MCC Chemistry department,12.92123,80.12365
+40,Marasmius siccus 1,MCC Botany department Road,12.92,80.12086
+41,Marasmius midnapurensis 1,MCC Science block,12.92123,80.12363
+42,Marasmius sp1,MCC Botany Road,12.91973,80.12087
+43,Schizophyllum commune,Thomas hall Road,12.92196,80.11889
+44,Lentinus zeyheri,MCC Farm,12.9161,80.12467
+45,Lentinus sajor-caju,MCC Farm,12.9161,80.12465
+46,Lentinus sqarrosulus,MCC Barnes hall Road,12.91954,80.11766
+47,Polyporous alveolaris,Near Botany department,12.91974,80.12063
+48,Polyporous grammosephalus,Near IOB Bank,12.92278,80.12386
+49,Phellinus rimosus,Near IACS,12.91933,80.12107
+50,Hexagonia tenuis,Near IOB Bank,12.922718,80.12366

data/recognition_log.csv

@@ -0,0 +1,36 @@
+timestamp,species,confidence,location,lat,lon,status
+2026-02-02 20:27:49,Unknown,0.1417810171842575,,,,not_found
+2026-02-02 20:30:35,Unknown,0.1050124317407608,,,,not_found
+2026-02-02 20:37:29,Agaricus placomyces,0.9987189769744872,MCC Infirmary,12.92088,80.12301,success
+2026-02-02 20:38:08,Chlorophyllum molybdites 1,0.9686679244041444,MCC IOB Road,12.92205,80.12304,success
+2026-02-02 20:39:05,Chlorophyllum molybdites 1,0.9529511332511902,MCC IOB Road,12.92205,80.12304,success
+2026-02-02 20:39:09,Chlorophyllum molybdites 1,0.9529511332511902,MCC IOB Road,12.92205,80.12304,success
+2026-02-02 21:05:55,Lepiota sp1,0.1816380321979522,MCC Botany Tank,12.92052,80.12086,success
+2026-02-02 21:06:48,Unknown,0.0808633044362068,,,,not_found
+2026-02-02 21:17:03,Lepiota sp1,0.1816380321979522,MCC Botany Tank,12.92052,80.12086,success
+2026-02-05 19:22:25,Leucocoprinus birnbaumii,0.6153523325920105,MCC Pavilion,12.91865,80.1213,success
+2026-02-05 19:23:19,Lepiota citriodora,0.3851979374885559,MCC Lake road,12.91644,80.11697,success
+2026-02-05 19:23:23,Lepiota citriodora,0.3851979374885559,MCC Lake road,12.91644,80.11697,success
+2026-02-05 19:23:25,Lepiota citriodora,0.3851979374885559,MCC Lake road,12.91644,80.11697,success
+2026-02-05 19:25:05,Leucocoprinus rubrotinctus,0.4666015207767486,MCC Botany Road,12.91978,80.12077,success
+2026-02-05 19:25:26,Amanita sp1,0.2804426550865173,MCC Botany Road,12.91988,80.12079,success
+2026-02-05 19:26:57,Unknown,0.2804426550865173,,,,not_found
+2026-02-05 19:28:11,Unknown,0.2804426550865173,,,,not_found
+2026-02-05 19:28:50,Unknown,0.2804426550865173,,,,not_found
+2026-02-05 19:29:15,Unknown,0.2804426550865173,,,,not_found
+2026-02-05 19:29:16,Leucocoprinus birnbaumii,0.8,MCC Pavilion,12.91865,80.1213,groq_success
+2026-02-05 19:30:51,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:31:29,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:33:39,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:35:26,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:35:28,The mushroom in the image exhibits a few distinctive features,0.85,,,,not_at_mcc
+2026-02-05 19:40:29,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:40:30,Error: 'choices',0.85,,,,not_at_mcc
+2026-02-05 19:41:42,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:41:42,API Error: No endpoints found for google/gemini-2.0-flash-exp:free.,0.85,,,,not_at_mcc
+2026-02-05 19:45:47,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:45:58,Agaricus trisulpurates,0.85,MCC IOB Road,12.92206,80.12306,vlm_success
+2026-02-05 19:46:20,Unknown,0.2804426550865173,,,,not_found
+2026-02-05 19:46:56,Leucocoprinus rubrotinctus,0.85,MCC Botany Road,12.91978,80.12077,vlm_success
+2026-02-05 19:50:23,Unknown,0.4511626660823822,,,,not_found
+2026-02-05 19:50:31,Agaricus trisulpurates,0.85,MCC IOB Road,12.92206,80.12306,vlm_success

requirements.txt

@@ -0,0 +1,9 @@
+fastapi==0.109.0
+uvicorn[standard]==0.27.0
+python-multipart==0.0.9
+pandas==2.1.4
+pillow==10.2.0
+torch==2.1.2
+open-clip-torch==2.24.0
+python-dotenv==1.0.1
+requests==2.31.0