63 | | * |
64 | | * |
65 | | * |
| 62 | * Divide data into “chunks” for faster and more efficient transmission |
| 63 | * Design experiments to test different architectures and implementations of Early Exiting and Split Computing |
| 64 | * Track and add Age of Information Metrics |
| 65 | |
| 66 | == Week 5 |
| 67 | **Summary** |
| 68 | * Figured out how to properly split a NN using split computing |
| 69 | * First Experimented with image inferencing on the same device |
| 70 | * Split the Neural Network(ResNet 18) onto two different devices |
| 71 | * Ran an inference with the split NN across a network |
| 72 | |
| 73 | **Next Steps** |
| 74 | * Take a step back |
| 75 | * Ask: what questions do we want to answer? |
| 76 | * As you vary the threshold for asking for help, how does the average latency change(over the dataset)? |
| 77 | Open ended |
| 78 | |
| 79 | Transfer to Precision time protocol(PTP) |
| 80 | |