DenseNet-121 is a densely connected CNN (~8M parameters) with high accuracy per parameter. 224x224 RGB in, 1000 ImageNet class scores out.
DenseNet-121 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.
1# any VKNN example binary, e.g. the IO runner:
2./vknn_run_io densenet121_fp16.vxm out_dir input.bin
