mmpretrain/docs/model_zoo.md

Model Zoo

ImageNet

ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. The ResNet family models below are trained by standard data augmentations, i.e., RandomResizedCrop, RandomHorizontalFlip and Normalize.

Model	Params(M)	Flops(G)	Top-1 (%)	Top-5 (%)	Download
ResNet-18	11.69	1.82	70.07	89.44	model | log
ResNet-34	21.8	3.68	73.85	91.53	model | log
ResNet-50	25.56	4.12	76.55	93.15	model | log
ResNet-101	44.55	7.85	78.18	94.03	model | log
ResNeSt-50	27.48	5.41	81.13	95.59	model | log
ResNeSt-101	48.28	10.27	82.32	96.24	model | log
ResNeSt-200	70.2	17.53	82.41	96.22	model | log
ResNeSt-269	110.93	22.58	82.70	96.28	model | log
ResNet-152	60.19	11.58	78.63	94.16	model | log
ResNetV1D-50	25.58	4.36	77.4	93.66	model | log
ResNetV1D-101	44.57	8.09	78.85	94.38	model | log
ResNetV1D-152	60.21	11.82	79.35	94.61	model | log
ResNeXt-32x4d-50	25.03	4.27	77.92	93.74	model | log
ResNeXt-32x4d-101	44.18	8.03	78.7	94.34	model | log
ResNeXt-32x8d-101	88.79	16.5	79.22	94.52	model | log
ResNeXt-32x4d-152	59.95	11.8	79.06	94.47	model | log
SE-ResNet-50	28.09	4.13	77.74	93.84	model | log
SE-ResNet-101	49.33	7.86	78.26	94.07	model | log
ShuffleNetV1 1.0x (group=3)	1.87	0.146	68.13	87.81	model | log
ShuffleNetV2 1.0x	2.28	0.149	69.55	88.92	model | log
MobileNet V2	3.5	0.319	71.86	90.42	model | log

Models with * are converted from other repos, others are trained by ourselves.

CIFAR10

Model	Params(M)	Flops(G)	Top-1 (%)	Download
ResNet-18-b16x8	11.17	0.56	94.72	model | log
ResNet-34-b16x8	21.28	1.16	95.34	model | log
ResNet-50-b16x8	23.52	1.31	95.36	model | log
ResNet-101-b16x8	42.51	2.52	95.66	model | log
ResNet-152-b16x8	58.16	3.74	95.96	model | log