This implementation contains code to test ResNet-152 image classification model across different hardware types (CPU, GPU, TPU) using Google Colab.

Running on Google Colab

1. Open Google Colab
2. Create a new notebook
3. Copy and paste the entire contents of the appropriate Python file into a Colab cell
4. Run the cell

Runtime Selection

For CPU/GPU testing, use colab_test.py where there is an automatic runtime detection. For TPU testing, use colab_test_tpu.py, since TPU runtime need some specific setup.

What It Does

• Loads Microsoft ResNet-152 model (~60M parameters, ~230MB)
• Calculates theoretical model size
• Processes a test image
• Measures and reports prediction time
• Displays top 5 classification results

Record the prediction times across different hardware types to compare performance characteristics.