@@ -119,43 +119,43 @@ CUDA_VISIBLE_DEVICES=0,1,2,3 python main.py
119119
120120# Performances and checkpoints
121121## full resolution on Cityscapes
122- | Model | Year | Encoder | Params (M) <br > paper / my | FPS<sup >1</sup > | mIoU (paper) <br > val / test| mIoU (my) val<sup >2</sup >|
123- | : ---: | : ---: | : ---: | : ---: | : ---: | : ---: | : ---: |
124- | ADSCNet | 2019 | None | n.a. / 0.51 | 89 | n.a. / 67.5 | [ 69.06] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/adscnet.pth ) |
125- | AGLNet | 2020 | None | 1.12 / 1.02 | 61 | 69.39 / 70.1 | [ 73.58] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/aglnet.pth ) |
126- | BiSeNetv1 | 2018 | ResNet18 | 49.0 / 13.32 | 88 | 74.8 / 74.7 | [ 74.91] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/bisenetv1.pth ) |
127- | BiSeNetv2 | 2020 | None | n.a. / 2.27 | 142 | 73.4 / 72.6 | [ 73.73<sup >3</sup >] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/bisenetv2-aux.pth ) |
128- | CANet | 2019 | MobileNetv2 | 4.8 / 4.77 | 76 | 73.4 / 73.5 | [ 76.59] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/canet.pth ) |
129- | CFPNet | 2021 | None | 0.55 / 0.27 | 64 | n.a. / 70.1 | [ 70.08] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/cfpnet.pth ) |
130- | CGNet | 2018 | None | 0.41 / 0.24 | 157 | 59.7 / 64.8<sup >4</sup > | [ 67.25] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/cgnet.pth ) |
131- | ContextNet | 2018 | None | 0.85 / 1.01 | 80 | 65.9 / 66.1 | [ 66.61] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/contextnet.pth ) |
132- | DABNet | 2019 | None | 0.76 / 0.75 | 140 | n.a. / 70.1 | [ 70.78] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/dabnet.pth ) |
133- | DDRNet | 2021 | None | 5.7 / 5.54 | 233 | 77.8 / 77.4 | [ 74.34] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ddrnet-23-slim.pth ) |
134- | DFANet | 2019 | XceptionA | 7.8 / 3.05 | 60 | 71.9 / 71.3 | [ 65.28] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/dfanet-a.pth ) |
135- | EDANet | 2018 | None | 0.68 / 0.69 | 125 | n.a. / 67.3 | [ 70.76] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/edanet.pth ) |
136- | ENet | 2016 | None | 0.37 / 0.37 | 140 | n.a. / 58.3 | [ 71.31] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/enet.pth ) |
137- | ERFNet | 2017 | None | 2.06 / 2.07 | 60 | 70.0 / 68.0 | [ 76.00] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/erfnet.pth ) |
138- | ESNet | 2019 | None | 1.66 / 1.66 | 66 | n.a. / 70.7 | [ 71.82] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/esnet.pth ) |
139- | ESPNet | 2018 | None | 0.36 / 0.38 | 111 | n.a. / 60.3 | [ 66.39] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/espnet.pth ) |
140- | ESPNetv2 | 2018 | None | 1.25 / 0.86 | 101 | 66.4 / 66.2 | [ 70.35] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/espnetv2.pth ) |
141- | FarseeNet | 2020 | ResNet18 | n.a. / 16.75 | 130 | 73.5 / 70.2 | [ 77.35] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/farseenet.pth ) |
142- | FastSCNN | 2019 | None | 1.11 / 1.02 | 358 | 68.6 / 68.0 | [ 69.37] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fastscnn.pth ) |
143- | FDDWNet | 2019 | None | 0.80 / 0.77 | 51 | n.a. / 71.5 | [ 75.86] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fddwnet.pth ) |
144- | FPENet | 2019 | None | 0.38 / 0.36 | 90 | n.a. / 70.1 | [ 72.05] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fpenet.pth ) |
145- | FSSNet | 2018 | None | 0.2 / 0.20 | 121 | n.a. / 58.8 | [ 65.44] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fssnet.pth ) |
146- | ICNet | 2017 | ResNet18 | 26.5<sup >5</sup > / 12.42 | 102 | 67.7<sup >5</sup > / 69.5<sup >5</sup > | [ 69.65] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/icnet.pth ) |
147- | LEDNet | 2019 | None | 0.94 / 1.46 | 76 | n.a. / 70.6 | [ 72.63] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/lednet.pth ) |
148- | LinkNet | 2017 | ResNet18 | 11.5 / 11.54 | 106 | n.a. / 76.4| [ 73.39] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/linknet.pth ) |
149- | LiteSeg | 2019 | MobileNetv2 | 4.38 / 4.29 | 117 | 70.0 / 67.8| [ 76.10] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/liteseg.pth ) |
150- | MiniNet | 2019 | None | 3.1 / 1.41 | 254 | n.a. / 40.7| [ 61.47] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/mininet.pth ) |
151- | MiniNetv2 | 2020 | None | 0.5 / 0.51 | 86 | n.a. / 70.5| [ 71.79] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/mininetv2.pth ) |
152- | PP-LiteSeg | 2022 | STDC1 | n.a. / 6.33 | 201 | 76.0 / 74.9| [ 72.49] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ppliteseg_stdc1.pth ) |
153- | PP-LiteSeg | 2022 | STDC2 | n.a. / 10.56 | 136 | 78.2 / 77.5| [ 74.37] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ppliteseg_stdc2.pth ) |
154- | RegSeg | 2021 | None | 3.34 / 3.37 | 104 | 78.5 / 78.3| 74.28 |
155- | SegNet | 2015 | None | 29.46 / 29.48 | 14 | n.a. / 56.1| [ 70.77] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/segnet.pth ) |
156- | ShelfNet | 2018 | ResNet18 | 23.5 / 16.04 | 110 | n.a. / 74.8| [ 77.63] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/shelfnet.pth ) |
157- | SQNet | 2016 | SqueezeNet-1.1 | n.a. / 4.81 | 69 | n.a. / 59.8| [ 69.55] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/sqnet.pth ) |
158- | SwiftNet | 2019 | ResNet18 | 11.8 / 11.95 | 141 | 75.4 / 75.5| [ 75.43] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/swiftnet.pth ) |
122+ | Model | Year | Encoder | Params (M) <br > paper / my| FPS<sup >1</sup > | mIoU (paper) <br > val / test | mIoU (my) val<sup >2</sup > |
123+ | ------------- | ---- | -------------- | ------------------------- | ----------------- | ------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
124+ | ADSCNet | 2019 | None | n.a. / 0.51 | 89 | n.a. / 67.5 | [ 69.06] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/adscnet.pth ) |
125+ | AGLNet | 2020 | None | 1.12 / 1.02 | 61 | 69.39 / 70.1 | [ 73.58] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/aglnet.pth ) |
126+ | BiSeNetv1 | 2018 | ResNet18 | 49.0 / 13.32 | 88 | 74.8 / 74.7 | [ 74.91] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/bisenetv1.pth ) |
127+ | BiSeNetv2 | 2020 | None | n.a. / 2.27 | 142 | 73.4 / 72.6 | [ 73.73<sup >3</sup >] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/bisenetv2-aux.pth ) |
128+ | CANet | 2019 | MobileNetv2 | 4.8 / 4.77 | 76 | 73.4 / 73.5 | [ 76.59] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/canet.pth ) |
129+ | CFPNet | 2021 | None | 0.55 / 0.27 | 64 | n.a. / 70.1 | [ 70.08] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/cfpnet.pth ) |
130+ | CGNet | 2018 | None | 0.41 / 0.24 | 157 | 59.7 / 64.8<sup >4</sup > | [ 67.25] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/cgnet.pth ) |
131+ | ContextNet | 2018 | None | 0.85 / 1.01 | 80 | 65.9 / 66.1 | [ 66.61] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/contextnet.pth ) |
132+ | DABNet | 2019 | None | 0.76 / 0.75 | 140 | n.a. / 70.1 | [ 70.78] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/dabnet.pth ) |
133+ | DDRNet | 2021 | None | 5.7 / 5.54 | 233 | 77.8 / 77.4 | [ 74.34] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ddrnet-23-slim.pth ) |
134+ | DFANet | 2019 | XceptionA | 7.8 / 3.05 | 60 | 71.9 / 71.3 | [ 65.28] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/dfanet-a.pth ) |
135+ | EDANet | 2018 | None | 0.68 / 0.69 | 125 | n.a. / 67.3 | [ 70.76] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/edanet.pth ) |
136+ | ENet | 2016 | None | 0.37 / 0.37 | 140 | n.a. / 58.3 | [ 71.31] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/enet.pth ) |
137+ | ERFNet | 2017 | None | 2.06 / 2.07 | 60 | 70.0 / 68.0 | [ 76.00] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/erfnet.pth ) |
138+ | ESNet | 2019 | None | 1.66 / 1.66 | 66 | n.a. / 70.7 | [ 71.82] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/esnet.pth ) |
139+ | ESPNet | 2018 | None | 0.36 / 0.38 | 111 | n.a. / 60.3 | [ 66.39] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/espnet.pth ) |
140+ | ESPNetv2 | 2018 | None | 1.25 / 0.86 | 101 | 66.4 / 66.2 | [ 70.35] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/espnetv2.pth ) |
141+ | FarseeNet | 2020 | ResNet18 | n.a. / 16.75 | 130 | 73.5 / 70.2 | [ 77.35] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/farseenet.pth ) |
142+ | FastSCNN | 2019 | None | 1.11 / 1.02 | 358 | 68.6 / 68.0 | [ 69.37] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fastscnn.pth ) |
143+ | FDDWNet | 2019 | None | 0.80 / 0.77 | 51 | n.a. / 71.5 | [ 75.86] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fddwnet.pth ) |
144+ | FPENet | 2019 | None | 0.38 / 0.36 | 90 | n.a. / 70.1 | [ 72.05] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fpenet.pth ) |
145+ | FSSNet | 2018 | None | 0.2 / 0.20 | 121 | n.a. / 58.8 | [ 65.44] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/fssnet.pth ) |
146+ | ICNet | 2017 | ResNet18 | 26.5<sup >5</sup > / 12.42 | 102 | 67.7<sup >5</sup > / 69.5<sup >5</sup > | [ 69.65] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/icnet.pth ) |
147+ | LEDNet | 2019 | None | 0.94 / 1.46 | 76 | n.a. / 70.6 | [ 72.63] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/lednet.pth ) |
148+ | LinkNet | 2017 | ResNet18 | 11.5 / 11.54 | 106 | n.a. / 76.4 | [ 73.39] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/linknet.pth ) |
149+ | LiteSeg | 2019 | MobileNetv2 | 4.38 / 4.29 | 117 | 70.0 / 67.8 | [ 76.10] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/liteseg.pth ) |
150+ | MiniNet | 2019 | None | 3.1 / 1.41 | 254 | n.a. / 40.7 | [ 61.47] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.1/mininet.pth ) |
151+ | MiniNetv2 | 2020 | None | 0.5 / 0.51 | 86 | n.a. / 70.5 | [ 71.79] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/mininetv2.pth ) |
152+ | PP-LiteSeg | 2022 | STDC1 | n.a. / 6.33 | 201 | 76.0 / 74.9 | [ 72.49] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ppliteseg_stdc1.pth ) |
153+ | PP-LiteSeg | 2022 | STDC2 | n.a. / 10.56 | 136 | 78.2 / 77.5 | [ 74.37] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/ppliteseg_stdc2.pth ) |
154+ | RegSeg | 2021 | None | 3.34 / 3.37 | 104 | 78.5 / 78.3 | 74.28 |
155+ | SegNet | 2015 | None | 29.46 / 29.48 | 14 | n.a. / 56.1 | [ 70.77] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/segnet.pth ) |
156+ | ShelfNet | 2018 | ResNet18 | 23.5 / 16.04 | 110 | n.a. / 74.8 | [ 77.63] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/shelfnet.pth ) |
157+ | SQNet | 2016 | SqueezeNet-1.1 | n.a. / 4.81 | 69 | n.a. / 59.8 | [ 69.55] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/sqnet.pth ) |
158+ | SwiftNet | 2019 | ResNet18 | 11.8 / 11.95 | 141 | 75.4 / 75.5 | [ 75.43] ( https://github.com/zh320/realtime-semantic-segmentation-pytorch/releases/download/v1.0/swiftnet.pth ) |
159159
160160[ <sup >1</sup >FPSs are evaluated on RTX 2080 at resolution 1024x512 using this [ script] ( tools/test_speed.py )]
161161[ <sup >2</sup >These results are obtained by training 800 epochs with crop-size 1024x1024]
0 commit comments