Add Streamlit web interface for benchmark execution

[Copilot]

Implements an interactive web UI for running ResNet inference benchmarks across PyTorch, ONNX, OpenVINO, and TensorRT backends.

Changes

New streamlit_app.py

• Image selection via file upload or sample gallery
• Mode selection (cpu/cuda/onnx/ov/tensorrt/all) with GPU detection
• Real-time benchmark execution with progress indicators
• Results display: predictions with confidence scores, avg inference time, throughput metrics

Dependencies

• Added streamlit>=1.41.0 for web interface
• Added onnxscript>=0.5.0 (required for PyTorch ONNX export)
• Fixed pyproject.toml author email validation

Documentation

• Updated README with Streamlit instructions (marked as recommended option)
• Added interface screenshots demonstrating image selection, configuration, and results display

Usage

streamlit run streamlit_app.py

Replaces command-line workflow:

# Before: CLI with flags
python main.py --topk 3 --mode=all --image_path="./inference/cat3.jpg"

# After: Interactive UI with dropdowns and sliders

Screenshots

Interface

Results Display

Notes

Platform-agnostic temp file handling using flag-based tracking instead of path prefix checks. No breaking changes to existing CLI interface.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• checkip.amazonaws.com
  • Triggering command: /usr/bin/python3 /home/REDACTED/.local/bin/streamlit run streamlit_app.py --server.headless=true --server.port=8501 (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

Create streamlit interface to work with benchamrk.

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.