squeezenet for VKNN — fp16, full-GPU
SqueezeNet 1.1 image classifier (torchvision export), compiled for the VKNN Vulkan inference engine. Every op runs on the GPU (fp16 weights + fp16 compute, fp32 host boundary); the CPU backend serves as the bit-accuracy oracle in VKNN's device gates, and this model's GPU outputs are gated against an fp32 onnxruntime golden (cosine > 0.999, argmax agreement) on-device.
| File | squeezenet_fp16.vxm (2.4M) |
| Input | input [1x3x224x224] (NCHW fp32) |
| Container | VXM3 (single graph, weights embedded) |
Run
# any VKNN example binary, e.g. the IO runner:
./vknn_run_io squeezenet_fp16.vxm out_dir input.bin
Recompile from your own ONNX with vknn_compile model.onnx out.vxm --fp16.