@@ -127,29 +127,29 @@ I've leveraged the training scripts in this repository to train a few of the mod
127127#### @ 224x224
128128| Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling | Source |
129129| ---| ---| ---| ---| ---| ---|
130- | senet154 | 81.224 (18.776) | 95.356 (4.644) | 115.09 | bicubic | |
131- | resnet152_v1s | 81.012 (18.988) | 95.416 (4.584) | 60.32 | bicubic | |
132- | seresnext101_32x4d | 80.902 (19.098) | 95.294 (4.706) | 48.96 | bicubic | |
133- | seresnext101_64x4d | 80.890 (19.110) | 95.304 (4.696) | 88.23 | bicubic | |
134- | resnext101_64x4d | 80.602 (19.398) | 94.994 (5.006) | 83.46 | bicubic | |
135- | resnet152_v1d | 80.470 (19.530) | 95.206 (4.794) | 60.21 | bicubic | |
136- | resnet101_v1d | 80.424 (19.576) | 95.020 (4.980) | 44.57 | bicubic | |
137- | resnext101_32x4d | 80.334 (19.666) | 94.926 (5.074) | 44.18 | bicubic | |
138- | resnet101_v1s | 80.300 (19.700) | 95.150 (4.850) | 44.67 | bicubic | |
139- | resnet152_v1c | 79.916 (20.084) | 94.842 (5.158) | 60.21 | bicubic | |
140- | seresnext50_32x4d | 79.912 (20.088) | 94.818 (5.182) | 27.56 | bicubic | |
141- | resnet152_v1b | 79.692 (20.308) | 94.738 (5.262) | 60.19 | bicubic | |
142- | resnet101_v1c | 79.544 (20.456) | 94.586 (5.414) | 44.57 | bicubic | |
143- | resnext50_32x4d | 79.356 (20.644) | 94.424 (5.576) | 25.03 | bicubic | |
144- | resnet101_v1b | 79.304 (20.696) | 94.524 (5.476) | 44.55 | bicubic | |
145- | resnet50_v1d | 79.074 (20.926) | 94.476 (5.524) | 25.58 | bicubic | |
146- | resnet50_v1s | 78.712 (21.288) | 94.242 (5.758) | 25.68 | bicubic | |
147- | resnet50_v1c | 78.010 (21.990) | 93.988 (6.012) | 25.58 | bicubic | |
148- | resnet50_v1b | 77.578 (22.422) | 93.718 (6.282) | 25.56 | bicubic | |
149- | resnet34_v1b | 74.580 (25.420) | 91.988 (8.012) | 21.80 | bicubic | |
130+ | gluon_senet154 | 81.224 (18.776) | 95.356 (4.644) | 115.09 | bicubic | |
131+ | gluon_resnet152_v1s | 81.012 (18.988) | 95.416 (4.584) | 60.32 | bicubic | |
132+ | gluon_seresnext101_32x4d | 80.902 (19.098) | 95.294 (4.706) | 48.96 | bicubic | |
133+ | gluon_seresnext101_64x4d | 80.890 (19.110) | 95.304 (4.696) | 88.23 | bicubic | |
134+ | gluon_resnext101_64x4d | 80.602 (19.398) | 94.994 (5.006) | 83.46 | bicubic | |
135+ | gluon_resnet152_v1d | 80.470 (19.530) | 95.206 (4.794) | 60.21 | bicubic | |
136+ | gluon_resnet101_v1d | 80.424 (19.576) | 95.020 (4.980) | 44.57 | bicubic | |
137+ | gluon_resnext101_32x4d | 80.334 (19.666) | 94.926 (5.074) | 44.18 | bicubic | |
138+ | gluon_resnet101_v1s | 80.300 (19.700) | 95.150 (4.850) | 44.67 | bicubic | |
139+ | gluon_resnet152_v1c | 79.916 (20.084) | 94.842 (5.158) | 60.21 | bicubic | |
140+ | gluon_seresnext50_32x4d | 79.912 (20.088) | 94.818 (5.182) | 27.56 | bicubic | |
141+ | gluon_resnet152_v1b | 79.692 (20.308) | 94.738 (5.262) | 60.19 | bicubic | |
142+ | gluon_resnet101_v1c | 79.544 (20.456) | 94.586 (5.414) | 44.57 | bicubic | |
143+ | gluon_resnext50_32x4d | 79.356 (20.644) | 94.424 (5.576) | 25.03 | bicubic | |
144+ | gluon_resnet101_v1b | 79.304 (20.696) | 94.524 (5.476) | 44.55 | bicubic | |
145+ | gluon_resnet50_v1d | 79.074 (20.926) | 94.476 (5.524) | 25.58 | bicubic | |
146+ | gluon_resnet50_v1s | 78.712 (21.288) | 94.242 (5.758) | 25.68 | bicubic | |
147+ | gluon_resnet50_v1c | 78.010 (21.990) | 93.988 (6.012) | 25.58 | bicubic | |
148+ | gluon_resnet50_v1b | 77.578 (22.422) | 93.718 (6.282) | 25.56 | bicubic | |
149+ | gluon_resnet34_v1b | 74.580 (25.420) | 91.988 (8.012) | 21.80 | bicubic | |
150150| SE-MNASNet 1.00 (A1) | 73.086 (26.914) | 91.336 (8.664) | 3.87 | bicubic | [ Google TFLite] ( https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet ) |
151151| MNASNet 1.00 (B1) | 72.398 (27.602) | 90.930 (9.070) | 4.36 | bicubic | [ Google TFLite] ( https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet )
152- | resnet18_v1b | 70.830 (29.170) | 89.756 (10.244) | 11.69 | bicubic | |
152+ | gluon_resnet18_v1b | 70.830 (29.170) | 89.756 (10.244) | 11.69 | bicubic | |
153153
154154#### @ 299x299
155155| Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling | Source |
0 commit comments