Table 1 Layer precision for each model version (FP = floating-point; B = binary; Q = quantized).
From: Memory-efficient low-compute segmentation algorithms for bladder-monitoring smart ultrasound devices
Model version | FP model | B+FP model | B+Q model |
|---|---|---|---|
Most conv layers | FP | Binary | Binary |
First layer | FP | FP | 4-bit input + 4-bit weight |
Skip connections | FP | FP | 4-bit/6-bit with scalable range per connection |
BatchNorm | FP | FP | Binary shift + 4-bit bias |
Activation function | ReLU | PReLU with FP \(\beta\), \(\gamma\) & \(\eta\) | PReLU with 2-bit \(\beta\) and 4-bit \(\gamma\) & \(\eta\) |
RSign | – | FP threshold (\(\alpha\)) | 4-bit threshold (\(\alpha\)) |
