You can deploy this model and start earning money today!

katolikov/
squeezenet-vknn

Name: squeezenet-vknn
Availability: InStock

Views

No views yet

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

bash

# 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.

katolikov/squeezenet-vknn

squeezenet for VKNN — fp16, full-GPU

Run

katolikov/
squeezenet-vknn