try new dockerfile

Dockerfile

@@ -1,4 +1,4 @@
-FROM docker.io/nvidia/cuda:12.3.2-cudnn9-devel-ubuntu22.04
+FROM nvidia/cuda:11.8.0-cudnn8-devel-ubuntu22.04
 
 # Set environment variables
 ENV DEBIAN_FRONTEND=noninteractive
@@ -25,74 +25,94 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
 # Set working directory
 WORKDIR /app
 
-# Copy requirements but modify TensorFlow version
+# Copy requirements.txt
 COPY requirements.txt /app/
-# Use TensorFlow 2.15.0 which has better compatibility with newer CUDA versions
-RUN sed -i 's/tensorflow==2.18.0/tensorflow==2.15.0/' /app/requirements.txt
 
-# Install Python dependencies
+# Install Python dependencies with specific compatible versions
 RUN pip3 install --no-cache-dir --upgrade pip setuptools wheel
-RUN pip3 install --no-cache-dir -r requirements.txt
-
-# Install compatible OpenCV
+# Install TensorFlow with GPU support (compatible with CUDA 11.8)
+RUN pip3 install --no-cache-dir tensorflow==2.12.0
+# Install other dependencies but skip tensorflow (already installed)
+RUN pip3 install --no-cache-dir --no-deps -r requirements.txt
+RUN pip3 install --no-cache-dir tensorflow-hub==0.14.0
 RUN pip3 install --no-cache-dir opencv-python-headless opencv-contrib-python-headless
 
 # Copy application code
 COPY . /app/
 
-# Create a more robust CPU fallback implementation
+# Create a robust CPU fallback implementation
 RUN echo 'import tensorflow as tf\n\
 import os\n\
-import sys\n\
 \n\
 # Set TensorFlow logging level\n\
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"\n\
 \n\
-# Function to modify FILM.py for CPU fallback\n\
-def ensure_cpu_fallback():\n\
-    # Check if we have a GPU available and supported\n\
+# Function to setup GPU with memory growth or fallback to CPU\n\
+def setup_tensorflow():\n\
     try:\n\
-        gpus = tf.config.list_physical_devices("GPU")\n\
-        if len(gpus) > 0:\n\
-            for gpu in gpus:\n\
-                tf.config.experimental.set_memory_growth(gpu, True)\n\
-            print(f"Available GPUs: {len(gpus)}")\n\
+        # List physical devices\n\
+        physical_devices = tf.config.list_physical_devices("GPU")\n\
+        if len(physical_devices) > 0:\n\
+            print(f"Found {len(physical_devices)} GPU(s)")\n\
+            for device in physical_devices:\n\
+                # Allow memory growth to avoid allocating all GPU memory at once\n\
+                tf.config.experimental.set_memory_growth(device, True)\n\
+                print(f"Enabled memory growth for {device}")\n\
         else:\n\
-            print("No GPUs found, will run on CPU only")\n\
+            print("No GPU found. Running on CPU.")\n\
     except Exception as e:\n\
-        print(f"Error setting up GPU: {e}")\n\
+        print(f"Error setting up TensorFlow: {e}")\n\
+        print("Disabling GPU and falling back to CPU")\n\
+        # Force CPU usage if there was an error with GPU setup\n\
+        os.environ["CUDA_VISIBLE_DEVICES"] = "-1"\n\
 \n\
-# Call the function\n\
-ensure_cpu_fallback()\n\
+# Call the setup function\n\
+setup_tensorflow()\n\
 ' > /app/tf_setup.py
 
-# Modify FILM.py to use CPU if GPU fails
+# Modify FILM.py to properly handle CPU fallback
 RUN if [ -f "/app/FILM.py" ]; then \
     # Import our setup at the top of the file\
-    sed -i '1s/^/import sys\nimport os\nimport tensorflow as tf\nfrom tf_setup import *\n/' /app/FILM.py && \
-    # Add try-except around model call\
-    sed -i '/def __call__/a\        try:' /app/FILM.py && \
-    sed -i '/result = self._model/i\            # Try with GPU' /app/FILM.py && \
-    sed -i '/result = self._model/a\        except Exception as e:\n            print(f"GPU inference failed: {e}, falling back to CPU")\n            with tf.device("/cpu:0"):\n                result = self._model(inputs, training=False)' /app/FILM.py; \
+    sed -i '1s/^/import tensorflow as tf\nfrom tf_setup import setup_tensorflow\n/' /app/FILM.py && \
+    # Add GPU check and CPU fallback in __init__\
+    sed -i '/def __init__/a\        # Check if GPU is disabled and use CPU if needed\n        if "CUDA_VISIBLE_DEVICES" in os.environ and os.environ["CUDA_VISIBLE_DEVICES"] == "-1":\n            print("GPU is disabled, using CPU for FILM")\n            self._device = "/cpu:0"\n        else:\n            self._device = "/gpu:0"\n        print(f"FILM will use device: {self._device}")' /app/FILM.py && \
+    # Add device context to __call__\
+    sed -i '/def __call__/a\        with tf.device(self._device):' /app/FILM.py && \
+    # Fix the model call indentation after adding the with statement\
+    sed -i 's/        result = self._model/            try:\n                result = self._model/g' /app/FILM.py && \
+    sed -i '/result = self._model/a\            except Exception as e:\n                print(f"Error during model inference: {e}, trying CPU fallback")\n                with tf.device("/cpu:0"):\n                    result = self._model(inputs, training=False)' /app/FILM.py; \
+    # Make sure os is imported if not already\
+    sed -i '1s/^/import os\n/' /app/FILM.py; \
 fi
 
 # Set environment variables for GPU compatibility
-ENV LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:/usr/local/cuda/lib64
+ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/lib/x86_64-linux-gnu:${LD_LIBRARY_PATH}
 ENV PATH=/usr/local/cuda/bin:${PATH}
+ENV CUDA_VISIBLE_DEVICES=0
 ENV TF_FORCE_GPU_ALLOW_GROWTH=true
 
-RUN ldconfig -p | grep cudnn
-
-# Expose port for Streamlit
-EXPOSE 8501
-
-# Create a startup script that ensures proper execution
+# Create a startup script with proper error handling
 RUN echo '#!/bin/bash\n\
-# Ensure library paths are set correctly\n\
-export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu:/usr/local/cuda/lib64\n\
-# Run the app\n\
+set -e\n\
+\n\
+# Check CUDA and cuDNN status\n\
+echo "CUDA libraries:"\n\
+ldconfig -p | grep cuda\n\
+echo "cuDNN libraries:"\n\
+ldconfig -p | grep cudnn\n\
+\n\
+# Test TensorFlow GPU\n\
+python3 -c "import tensorflow as tf; print(\\"Num GPUs Available: \\", len(tf.config.list_physical_devices(\\"GPU\\")))" || {\n\
+  echo "TensorFlow GPU test failed, falling back to CPU"\n\
+  export CUDA_VISIBLE_DEVICES=-1\n\
+}\n\
+\n\
+# Run the app with proper error handling\n\
 exec streamlit run app.py --server.port=8501 --server.address=0.0.0.0\n\
 ' > /app/start.sh && chmod +x /app/start.sh
 
+# Expose port for Streamlit
+EXPOSE 8501
+
 # Use the startup script
 CMD ["/app/start.sh"]