Unverified50% confidenceBenchmarkExact time
MobileNetV3 Large 版本在 ImageNet 上达到 75.2% Top-1 精度，推理延迟仅为 ResNet-50 的约 1/5
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn INT8-quantized MobileNet-v2 can complete a single image classification inference on an STM32H7 in approximately 100ms, with power consumption on the order of hundreds of milliwatts.64% similarUnverifiedMobileNetV3 采用深度可分离卷积，计算量约为标准卷积的 1/K²+1/C_out，当 K=3 且 C_out=256 时约为原来的 1/8 到 1/959% similarUnverifiedThe RTX 4060 can achieve generation speeds 3-5 times that of the GTX 1060.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810816API
curl https://kongchang.com/api/v1/knowledge/claims/810816MCP
get_claim(id=810816)