why the model size all so big?

[lucasjinreal]

compared with mbv2 and shufflenetv2 fasternet has a bigger size, this caused limitations deploy on edge devices.

[JierunChen]

Hi, FasterNet focuses on improving the accuracy-latency tradeoff but not on reducing the model size (slightly bigger than ShuffleNetV2 and MobileNetV2), as shown in the following table:

name	acc	#params	FLOPs	Throughput on GPU (fps)	Latency on CPU (ms)	Latency on ARM (ms)
ShuffleNetV2 x1.5	72.6	3.5M	0.30G	4878	12.1	266
MobileNetV2	72.0	3.5M	0.31G	4198	12.2	442
FasterNet-T0	71.9	3.9M	0.34G	6807	9.2	143
ShuffleNetV2 x2	74.9	7.4M	0.59G	3339	17.8	403
MobileNetV2	74.7	6.1M	0.60G	2711	22.6	650
FasterNet-T1	76.2	7.6M	0.85G	3782	17.7	285

[lucasjinreal]

@JierunChen hello, may I ask which framework used to get these values?

[JierunChen]

@JierunChen hello, may I ask which framework used to get these values?

We use FVcore for #params and FLOPs calculation. Code for measuring throughput/latency is provided in utils.py.

Note that when comparing the model size by storage, ensure all models compared have the same precision, e.g., 32 bits, 16 bits, or 8 bits.

[lucasjinreal]

@JierunChen thanks, seems mostly measuring on torch, have u tried export to onnx and measuring on onnxruntime? Since the speed actually highly related how optimized in forward frameworks.

[JierunChen]

@jinfagang No deployment engines are involved when measuring the latency/throughput. We haven't tried exporting to onnx. You are welcome to do so and try various deployment engines, e.g. OnnxRuntime, TensorRT, NCNN, etc.