Classifier Recipes: Supported Backbones

The following tables provide a list of classifier backbones that represent a range of performance options. These entries are the result of Latent AI testing hundreds of classifier backbones and selecting the models that provided the most accurate results for different target speeds in our device farm. The models are listed with the fastest at the top and more accurate models at the bottom. Accuracy may vary depending on your dataset. Keep in mind that the dataset used in the tutorial is small and should not be used for accuracy assessment.

Each of the models in the first table will work for applications targets ARM and x86, both CPU+GPU, and CPU only.

Latent AI provides a relative latency metric in addition to the backbone name in the first column (which you can pass to AF in Step One). This latency metric was determined through training and then testing the models on a cluster of a Raspberry Pi. The latency metric is dependent on hardware settings, quantization settings, memory, etc., so it is best used for relative comparison between the models.

The per-channel column indicates whether the backbone is compatible with our per-channel quantization for CPU only (x86, ARM) Int8 optimization. In many cases, you will get better accuracy using per-channel quantization on these models. Some models utilize operators that are currently unsupported by our Int8 optimization. Per-channel Int8 quantization is used by default for optimizations targeting GPU.

Table 1 - Classifier ML Recipe Variants

Table 2 shows additional models that do not currently support Int8 quantization for GPU in addition to the models listed above. The first four models may be of particular interest for low SWaP applications due to their relative latency on modest CPU architectures.

Table 2 - Classifier ML Recipe Variants - No GPU Int8 Support