Readme file changing, test bash script changing, Folder order changing (PROJECTS/DATA and PROJECTS/RESULTS)

Dockerfile

@@ -1,37 +1,110 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Builds ultralytics/ultralytics:latest image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
-# Image is CUDA-optimized for YOLO11 single/multi-GPU training and inference
-
-# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch or nvcr.io/nvidia/pytorch:23.03-py3
+# 📦 STEP 1: Use NVIDIA's Official PyTorch Image
 FROM nvcr.io/nvidia/pytorch:23.08-py3
+# 🔥 Comes pre-installed with:
+# - Ubuntu 22.04 including Python 3.10
+# - NVIDIA CUDA® 12.2.1
+# - NVIDIA cuBLAS 12.2.5.1
+# - NVIDIA cuDNN 8.9.4
+# - NVIDIA NCCL 2.18.3
+# - NVIDIA RAPIDS™ 23.06
+# - Apex
+# - rdma-core 39.0
+# - NVIDIA HPC-X 2.15
+# - OpenMPI 4.1.4+
+# - GDRCopy 2.3
+# - TensorBoard 2.9.0
+# - Nsight Compute 2023.2.1.3
+# - Nsight Systems 2023.2.3.1001
+# - NVIDIA TensorRT™ 8.6.1.6
+# - Torch-TensorRT 2.0.0.dev0
+# - NVIDIA DALI® 1.28.0
+# - MAGMA 2.6.2
+# - JupyterLab 2.3.2 including Jupyter-TensorBoard
+# - TransformerEngine 0.11.0++3f01b4f
+# - PyTorch quantization wheel 2.1.2
 
+# Saves time & ensures GPU compatibility!
+
+# 🛠 STEP 2: Install Basic Linux Packages
 RUN apt-get update && \
     apt-get install -y --no-install-recommends \
-    gcc git zip unzip wget curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 libsm6 \
+    gcc \                   
+    git \                   
+    zip unzip \             
+    wget curl \             
+    htop \                  
+    libgl1 \                
+    libglib2.0-0 \          
+    libpython3-dev \        
+    gnupg \                 
+    g++ \                   
+    libusb-1.0-0 \          
+    libsm6 \                
     && rm -rf /var/lib/apt/lists/*
+# 🚿 Clean-up: Shrinks the image size by removing cached lists
 
-# Security updates
-# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796
+# 🔐 STEP 3: Apply Security Updates for Core Packages
 RUN apt upgrade --no-install-recommends -y openssl tar
+# 🚨 Patch critical vulnerabilities in OpenSSL (network encryption) & tar (archives)
 
-# Create working directory
+# 📁 STEP 4: Set Working Directory
 WORKDIR /app
+# All following commands will execute in /app inside the container
 
-# Install requirements
+# 🧪 STEP 5: Install Python Requirements
 COPY requirements.txt .
 RUN pip install -r requirements.txt
+# 📦 Installs YOLOv7 dependencies (torchvision, opencv-python, numpy, etc.)
 
-
-# Install OpenCV with CUDA support
+# 📂 STEP 6: Copy Source Code to the Container
 COPY . .
-RUN rm -rf ./workspace
-RUN bash scripts/build_opencv.sh
+# ✅ Adds your whole project directory into the container at /app
 
-# Test CUDA and OpenCV support
+# 🧹 Clean Up Pre-existing Workspace (Optional)
+RUN rm -rf ./workspace
+# 💡 Ensures the build is fresh & avoids legacy artifacts
+
+# ⚙️ STEP 7: Build OpenCV with CUDA Support
+RUN bash scripts/build_opencv.sh
+# 🚀 This script compiles OpenCV from source with GPU acceleration for video/image ops
+# 😎 Perfect for fast inference on large datasets
+
+# ✅ STEP 8: Run Diagnostic Tests
 RUN bash scripts/test-cmds.sh
-RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt  # Recommend for lower specs
-# RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt
-# RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt  # Recommend for train_aux.py training
-# RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt
-# RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt
-RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt  # Recommend for high specs
+# 🧪 Verifies:
+# - OpenCV is properly installed
+# - CUDA is working
+# - Everything’s talking to each other correctly
+
+# ⬇️ STEP 9: Download YOLOv7 Pretrained Models
+# ⚠️ Choose the one that matches your hardware & use case
+
+# 🏃‍♂️ Lightweight Model – Fast AF
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
+# Use this for: 🔋 embedded systems, Raspberry Pi, Jetson Nano
+# Speed ✅ Accuracy ❌
+
+# 🧠 Balanced Model – Best for Most
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7x.pt
+# Use this for: 🧪 general object detection on mid-range GPUs
+# Speed ⚖️ Accuracy ⚖️
+
+# 🔧 Training-Ready – For Custom Datasets
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6.pt
+# Use this for: 🏋️‍♂️ training with `train_aux.py`
+# Comes with extra layers for learning better
+
+# 🎯 Precision Model – Accuracy First
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6.pt
+# Use this for: 📸 detection where precision matters
+# Speed ❌ Accuracy ✅✅
+
+# 🧬 Deep Variant – Alternate Heavyweight
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-d6.pt
+# Use this if: You’re experimenting or need d6-specific layers
+
+# 👑 Elite Model – Max Accuracy, Max Power
+RUN wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-e6e.pt
+# Use this for: 🖥️ high-end workstations, servers
+# Speed ❌❌ Accuracy 💯
+

PROJECTS/DATA/2024-05-28_061155_frame_00007.txt

@@ -0,0 +1 @@
+0 0.421296 0.127930 0.057870 0.074219

PROJECTS/DATA/2024-05-28_061658_frame_00000.txt

@@ -0,0 +1 @@
+0 0.451582 0.119141 0.063657 0.078125

PROJECTS/DATA/2024-05-28_061658_frame_00005.txt

@@ -0,0 +1 @@
+0 0.427662 0.118408 0.063657 0.084473

PROJECTS/DATA/2024-05-28_061658_frame_00006.txt

@@ -0,0 +1 @@
+0 0.424576 0.117188 0.069059 0.075195

PROJECTS/DATA/2024-05-28_061658_frame_00008.txt

@@ -0,0 +1 @@
+0 0.416088 0.120117 0.060571 0.077148

PROJECTS/DATA/2024-05-28_061658_frame_00009.txt

@@ -0,0 +1 @@
+0 0.412616 0.120361 0.070602 0.078613

PROJECTS/DATA/2024-05-28_062201_frame_00000.txt

@@ -0,0 +1 @@
+0 0.444059 0.120850 0.067130 0.077637

PROJECTS/DATA/2024-05-28_062201_frame_00001.txt

@@ -0,0 +1 @@
+0 0.440008 0.120605 0.060571 0.075195

README.md

@@ -44,7 +44,9 @@ Your existing machine to give a gpu capabilities to existing docker containers.
 
 If you have trouble about can not see cuda in your existing machine try `privileged` parameter:
 ```shell
-docker run --gpus all --privileged --rm -it barisx/yolov7-cuda-opencv:latest
+docker run --gpus all -it --rm --ipc=host --ulimit memlock=-1 --ulimit stack=67108864 --privileged \
+-v /home/grkm/Documents/yolov7-cuda-opencv/PROJECTS/DATA \
+-v /home/grkm/Documents/yolov7-cuda-opencv/PROJECTS/RESULTS \
 ```
 
 After you can check it:

scripts/test-cmds.sh

@@ -1,4 +1,89 @@
-python -c "import cv2;print(cv2.cuda.getCudaEnabledDeviceCount())"
-python3 -c "import cv2;print(cv2.cuda.getCudaEnabledDeviceCount())"
-dpkg -l | grep "opencv"
-python -c "import torch;print(torch.cuda.is_available())"
+#!/bin/bash
+
+# Title
+echo "🧪 SYSTEM DIAGNOSTIC TEST SCRIPT FOR AI/ML ENVIRONMENT"
+
+##########################
+# Function: Test OpenCV
+##########################
+test_opencv() {
+    echo "-------------------Testing OpenCV installation (START)---------------------"
+
+    echo "📦 Checking OpenCV installation and version..."
+    python3 -c "import cv2; print(f'  OpenCV version: {cv2.__version__}')"
+
+    echo "⚙️  Checking OpenCV build flags for CUDA..."
+    python3 -c "import cv2; print(cv2.getBuildInformation())" | grep "CUDA"
+
+    echo "🚀 Checking if OpenCV can access CUDA-enabled GPU..."
+    python3 -c "import cv2; print('  ✅ CUDA is enabled for OpenCV') if cv2.cuda.getCudaEnabledDeviceCount() else print('  ❌ CUDA is NOT enabled for OpenCV')"
+
+    echo "-------------------Testing OpenCV installation (END)---------------------"
+    echo "/"
+}
+
+##########################
+# Function: Test PyTorch
+##########################
+test_torch() {
+    echo "-------------------Testing PyTorch installation (START)---------------------"
+
+    echo "📦 Checking PyTorch installation and version..."
+    python3 -c "import torch; print(f'  Torch version: {torch.__version__}')"
+
+    echo "🚀 Checking if PyTorch can access CUDA-enabled GPU..."
+    python3 -c "import torch; print('  ✅ CUDA is enabled for Torch') if torch.cuda.is_available() else print('  ❌ CUDA is NOT enabled for Torch')"
+
+    echo "-------------------Testing PyTorch installation (END)---------------------"
+    echo "/"
+}
+
+##########################
+# Function: Test NVCC (CUDA Compiler)
+##########################
+test_nvcc() {
+    echo "-------------------Testing nvcc installation (START)---------------------"
+
+    echo "📦 Checking nvcc (NVIDIA CUDA Compiler) version..."
+    output=$(nvcc --version)
+
+    compiler=$(echo "$output" | grep "nvcc:" | cut -d ':' -f2- | sed 's/^/ /')
+    build_date=$(echo "$output" | grep "Built on" | sed 's/Built on //; s/_/ /g')
+    cuda_version=$(echo "$output" | grep "Cuda compilation tools" | sed -E 's/.*release ([^,]+), V([0-9\.]+).*/\1 (\2)/')
+    build_id=$(echo "$output" | grep "Build cuda")
+
+    echo "🧠 CUDA Compiler Information:"
+    echo "- Compiler: $compiler"
+    echo "- CUDA Version: $cuda_version"
+    echo "- Build Date: $build_date"
+    echo "- Internal Build ID: $build_id"
+
+    echo "-------------------Testing nvcc installation (END)---------------------"
+    echo "/"
+}
+
+##########################
+# Function: Test NVIDIA-SMI (Driver & GPU)
+##########################
+test_nvidia_smi() {
+    echo "-------------------Testing nvidia-smi installation (START)---------------------"
+
+    echo "🖥️  GPU and driver status:"
+    nvidia-smi
+
+    echo "-------------------Testing nvidia-smi installation (END)---------------------"
+}
+
+##########################
+# Main: Run All Tests
+##########################
+run_all_tests() {
+    test_opencv
+    test_torch
+    test_nvcc
+    test_nvidia_smi
+}
+
+# Execute
+run_all_tests
+echo "-------------------All tests completed!---------------------"