update space

.idea/workspace.xml

@@ -5,10 +5,10 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="27c9ae1a-a6fa-4472-8bcd-a7087620894b" name="Changes" comment="update space">
-      <change afterPath="$PROJECT_DIR$/scripts/populate_health_records.py" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/scripts/populate_inventory.py" afterDir="false" />
+      <change afterPath="$PROJECT_DIR$/training/resnet-18-model-for-poultry-disease-classification.ipynb" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/templates/chatbot.html" beforeDir="false" afterPath="$PROJECT_DIR$/templates/chatbot.html" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/app.py" beforeDir="false" afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/requirements.txt" beforeDir="false" afterPath="$PROJECT_DIR$/requirements.txt" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -51,24 +51,24 @@
     "RunOnceActivity.ShowReadmeOnStart": "true",
     "git-widget-placeholder": "main",
     "ignore.virus.scanning.warn.message": "true",
-    "last_opened_file_path": "C:/git/Generative_AI_with_poultry_disease_detection_system_v2/static",
+    "last_opened_file_path": "C:/git/Generative_AI_with_poultry_disease_detection_system_v2",
     "list.type.of.created.stylesheet": "CSS",
     "node.js.detected.package.eslint": "true",
     "node.js.detected.package.tslint": "true",
     "node.js.selected.package.eslint": "(autodetect)",
     "node.js.selected.package.tslint": "(autodetect)",
     "nodejs_package_manager_path": "npm",
-    "settings.editor.selected.configurable": "preferences.pluginManager",
+    "settings.editor.selected.configurable": "swagger",
     "vue.rearranger.settings.migration": "true"
   }
 }]]></component>
   <component name="RecentsManager">
     <key name="CopyFile.RECENT_KEYS">
+      <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2" />
       <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\static" />
       <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\templates\tasks" />
       <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\templates\todo" />
       <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\templates" />
-      <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\static\images" />
     </key>
     <key name="MoveFile.RECENT_KEYS">
       <recent name="C:\git\Generative_AI_with_poultry_disease_detection_system_v2\static\images" />
@@ -130,22 +130,6 @@
       <workItem from="1730397485849" duration="22781000" />
       <workItem from="1730454506390" duration="12672000" />
     </task>
-    <task id="LOCAL-00073" summary="update space">
-      <option name="closed" value="true" />
-      <created>1730399007546</created>
-      <option name="number" value="00073" />
-      <option name="presentableId" value="LOCAL-00073" />
-      <option name="project" value="LOCAL" />
-      <updated>1730399007546</updated>
-    </task>
-    <task id="LOCAL-00074" summary="update space">
-      <option name="closed" value="true" />
-      <created>1730399542427</created>
-      <option name="number" value="00074" />
-      <option name="presentableId" value="LOCAL-00074" />
-      <option name="project" value="LOCAL" />
-      <updated>1730399542427</updated>
-    </task>
     <task id="LOCAL-00075" summary="update space">
       <option name="closed" value="true" />
       <created>1730400686897</created>
@@ -522,7 +506,23 @@
       <option name="project" value="LOCAL" />
       <updated>1730488078280</updated>
     </task>
-    <option name="localTasksCounter" value="122" />
+    <task id="LOCAL-00122" summary="update space">
+      <option name="closed" value="true" />
+      <created>1730488664527</created>
+      <option name="number" value="00122" />
+      <option name="presentableId" value="LOCAL-00122" />
+      <option name="project" value="LOCAL" />
+      <updated>1730488664527</updated>
+    </task>
+    <task id="LOCAL-00123" summary="update space">
+      <option name="closed" value="true" />
+      <created>1730488911425</created>
+      <option name="number" value="00123" />
+      <option name="presentableId" value="LOCAL-00123" />
+      <option name="project" value="LOCAL" />
+      <updated>1730488911425</updated>
+    </task>
+    <option name="localTasksCounter" value="124" />
     <servers />
   </component>
   <component name="TypeScriptGeneratedFilesManager">

app.py

@@ -5,7 +5,7 @@ from fastapi import FastAPI, Request, HTTPException, BackgroundTasks, Depends
 from fastapi.templating import Jinja2Templates
 from fastapi.responses import HTMLResponse, RedirectResponse
 from fastapi.staticfiles import StaticFiles
-import tensorflow as tf
+# import tensorflow as tf
 import os
 import logging
 import time
@@ -20,9 +20,9 @@ from huggingface_hub import login
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 
-# Check GPU availability for TensorFlow
-gpu_devices = tf.config.list_physical_devices('GPU')
-logger.info(f"{'GPUs available' if gpu_devices else 'Using CPU'} for TensorFlow")
+# # Check GPU availability for TensorFlow
+# gpu_devices = tf.config.list_physical_devices('GPU')
+# logger.info(f"{'GPUs available' if gpu_devices else 'Using CPU'} for TensorFlow")
 
 # Initialize FastAPI app and templates
 app = FastAPI()

requirements.txt

@@ -1,11 +1,11 @@
-tensorflow[and-cuda]==2.13.0
+tensorflow[and-cuda]
 opencv-python-headless
 fastapi
 passlib[bcrypt]
 pydantic[email]
 pymongo
 python-dotenv
-python-jose[cryptography]==3.3.0
+python-jose[cryptography]
 starlette
 uvicorn
 jinja2

services/disease_detection_service.py

@@ -3,9 +3,7 @@
 import os
 import logging
 import threading
-import tensorflow as tf
 import torch
-from keras.models import load_model
 import cv2
 import numpy as np
 from huggingface_hub import login
@@ -30,18 +28,9 @@ config = configparser.ConfigParser()
 config.read('config.ini')
 logger.info("Configuration loaded from config.ini.")
 
-# Configure TensorFlow for GPU and mixed precision if supported
-gpu_devices = tf.config.list_physical_devices('GPU')
-if gpu_devices:
-    for gpu in gpu_devices:
-        tf.config.experimental.set_memory_growth(gpu, True)
-    if tf.config.experimental.get_device_details(gpu_devices[0]).get('compute_capability', (0, 0))[0] >= 7:
-        from tensorflow.keras import mixed_precision
-        policy = mixed_precision.Policy('mixed_float16')
-        mixed_precision.set_global_policy(policy)
-        logger.info("Mixed precision enabled on supported GPU.")
-else:
-    logger.info("No GPU detected, using CPU without mixed precision.")
+# Check for GPU availability and set device
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+logger.info(f"Using device: {device}")
 
 # Global model variables and threading event for synchronization
 disease_model = None
@@ -50,13 +39,12 @@ model_loading_event = threading.Event()
 
 # Function to load the disease detection model
 def load_disease_model():
-    """Load the pre-trained model for poultry disease detection."""
+    """Load the pre-trained PyTorch model for poultry disease detection."""
     try:
-        model_path = config.get('MODELS', 'DISEASE_MODEL_PATH', fallback="models/Final_Chicken_disease_model.h5")
-        device = tf.config.list_logical_devices('GPU')[0] if gpu_devices else tf.config.list_logical_devices('CPU')[0]
-        with tf.device(device.name):
-            model = load_model(model_path, compile=False)
-        logger.info(f"Disease detection model loaded successfully on {device.name}.")
+        model_path = config.get('MODELS', 'DISEASE_MODEL_PATH', fallback="models/Final_Chicken_disease_model.pth")
+        model = torch.load(model_path, map_location=device)
+        model.eval()  # Set model to evaluation mode
+        logger.info("Disease detection model loaded successfully.")
         return model
     except Exception as e:
         logger.error("Error loading disease detection model", exc_info=True)
@@ -64,29 +52,29 @@ def load_disease_model():
 
 # Function to load the Llama 3.2 model for language generation
 def load_llama_model():
-  """Load the Llama model and tokenizer for language generation."""
-  global llama_model, llama_tokenizer
-  try:
-      logger.info("Loading Llama 3.2 model and tokenizer using PyTorch-compatible model.")
-      model_name = "meta-llama/Llama-3.2-1B"  # Update with desired model name
-
-      # Load the tokenizer and model from the Hugging Face hub
-      llama_tokenizer = AutoTokenizer.from_pretrained(model_name)
-      llama_model = AutoModelForCausalLM.from_pretrained(model_name)
-
-      # Add a padding token if it's missing
-      if llama_tokenizer.pad_token is None:
-          logger.info("Adding padding token to tokenizer.")
-          llama_tokenizer.add_special_tokens({'pad_token': '[PAD]'})
-          llama_model.resize_token_embeddings(len(llama_tokenizer))
-
-      logger.info("Llama model and tokenizer loaded successfully.")
-      model_loading_event.set()  # Signal successful loading
-      return llama_model, llama_tokenizer
-  except Exception as e:
-      logger.error("Failed to load Llama model", exc_info=True)
-      model_loading_event.set()  # Ensure event is set even if loading fails
-      raise RuntimeError("Failed to load the Llama 3.2 model. Verify compatibility.")
+    """Load the Llama model and tokenizer for language generation."""
+    global llama_model, llama_tokenizer
+    try:
+        logger.info("Loading Llama 3.2 model and tokenizer using PyTorch-compatible model.")
+        model_name = "meta-llama/Llama-3.2-1B"  # Update with desired model name
+
+        # Load the tokenizer and model from the Hugging Face hub
+        llama_tokenizer = AutoTokenizer.from_pretrained(model_name)
+        llama_model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
+
+        # Add a padding token if it's missing
+        if llama_tokenizer.pad_token is None:
+            logger.info("Adding padding token to tokenizer.")
+            llama_tokenizer.add_special_tokens({'pad_token': '[PAD]'})
+            llama_model.resize_token_embeddings(len(llama_tokenizer))
+
+        logger.info("Llama model and tokenizer loaded successfully.")
+        model_loading_event.set()  # Signal successful loading
+        return llama_model, llama_tokenizer
+    except Exception as e:
+        logger.error("Failed to load Llama model", exc_info=True)
+        model_loading_event.set()  # Ensure event is set even if loading fails
+        raise RuntimeError("Failed to load the Llama 3.2 model. Verify compatibility.")
 
 # Disease mappings and recommended treatments
 name_disease = {0: 'Coccidiosis', 1: 'Healthy', 2: 'New Castle Disease', 3: 'Salmonella'}
@@ -106,15 +94,16 @@ class PoultryFarmBot:
         self.db = db
         logger.info("PoultryFarmBot initialized with MongoDB access.")
 
-    def preprocess_image(self, image: np.ndarray) -> np.ndarray:
+    def preprocess_image(self, image: np.ndarray) -> torch.Tensor:
         """Preprocess the input image for model prediction."""
         try:
             if image is None or image.size == 0:
                 raise ValueError("Invalid or empty image.")
             image = cv2.resize(image, (224, 224))
-            image = np.expand_dims(image, axis=0) / 255.0
+            image = np.transpose(image, (2, 0, 1))  # Change from HWC to CHW format for PyTorch
+            image = torch.tensor(image, dtype=torch.float32).unsqueeze(0) / 255.0
             logger.info("Image preprocessed successfully.")
-            return image
+            return image.to(device)
         except Exception as e:
             logger.error("Error in image preprocessing", exc_info=True)
             raise
@@ -123,12 +112,13 @@ class PoultryFarmBot:
         """Predict disease from preprocessed image and provide detailed results."""
         try:
             preprocessed_image = self.preprocess_image(image)
-            prediction = disease_model.predict(preprocessed_image)
-            predicted_class = np.argmax(prediction, axis=1).item()
+            with torch.no_grad():
+                prediction = disease_model(preprocessed_image)
+            predicted_class = torch.argmax(prediction, dim=1).item()
             disease_name = name_disease.get(predicted_class, "Unknown disease")
             disease_status = status_map.get(predicted_class, "Unknown status")
             recommendation = recommendations.get(predicted_class, "No recommendation available")
-            confidence = prediction[0][predicted_class] * 100
+            confidence = torch.softmax(prediction, dim=1)[0][predicted_class].item() * 100
             logger.info(f"Disease Prediction: {disease_name} with {confidence:.2f}% confidence.")
 
             # Generate a detailed response using Llama model
@@ -152,7 +142,7 @@ class PoultryFarmBot:
         """Generate a response from the Llama model based on a prompt."""
         try:
             max_length = min(len(prompt) + 50, 512)
-            inputs = llama_tokenizer(prompt, return_tensors="tf", max_length=max_length, truncation=True, padding=True)
+            inputs = llama_tokenizer(prompt, return_tensors="pt", max_length=max_length, truncation=True, padding=True).to(device)
             outputs = llama_model.generate(inputs["input_ids"], max_length=max_length, do_sample=True, temperature=0.7, top_p=0.9)
             return llama_tokenizer.decode(outputs[0], skip_special_tokens=True)
         except Exception as e: