Skip to content

V0.3.0-Weather-5-625-Weights
Compare
Choose a tag to compare
@Lupin1998 Lupin1998 released this 20 Jun 22:08
weather-5-625-weights
4faf1b5

We provide temperature prediction benchmark results on the popular WeatherBench dataset (temperature prediction t2m) using $12\rightarrow 12$ frames prediction setting. Metrics (MSE, MAE, SSIM, pSNR) of the best models are reported in three trials. Parameters (M), FLOPs (G), and V100 inference FPS (s) are also reported for all methods. All methods are trained by Adam optimizer with Cosine Annealing scheduler (no warmup and min lr is 1e-6).

STL Benchmarks on Temperature (t2m)

Method Setting Params FLOPs FPS MSE MAE RMSE Download
ConvLSTM 50 epoch 14.98M 136G 46 1.521 0.7949 1.233 model | log
E3D-LSTM 50 epoch 51.09M 169G 35 1.592 0.8059 1.262 model | log
PhyDNet 50 epoch 3.09M 36.8G 177 285.9 8.7370 16.91 model | log
PredRNN 50 epoch 23.57M 278G 22 1.331 0.7246 1.154 model | log
PredRNN++ 50 epoch 38.31M 413G 15 1.634 0.7883 1.278 model | log
MIM 50 epoch 37.75M 109G 126 1.784 0.8716 1.336 model | log
MAU 50 epoch 5.46M 39.6G 237 1.251 0.7036 1.119 model | log
PredRNNv2 50 epoch 23.59M 279G 22 1.545 0.7986 1.243 model | log
IncepU (SimVPv1) 50 epoch 14.67M 8.03G 160 1.238 0.7037 1.113 model | log
gSTA (SimVPv2) 50 epoch 12.76M 7.01G 504 1.105 0.6567 1.051 model | log
ViT 50 epoch 12.41M 7.99G 432 1.146 0.6712 1.070 model | log
Swin Transformer 50 epoch 12.42M 6.88G 581 1.143 0.6735 1.069 model | log
Uniformer 50 epoch 12.02M 7.45G 465 1.204 0.6885 1.097 model | log
MLP-Mixer 50 epoch 11.10M 5.92G 713 1.255 0.7011 1.119 model | log
ConvMixer 50 epoch 1.13M 0.95G 1705 1.267 0.7073 1.126 model | log
Poolformer 50 epoch 9.98M 5.61G 722 1.156 0.6715 1.075 model | log
ConvNeXt 50 epoch 10.09M 5.66G 689 1.277 0.7220 1.130 model | log
VAN 50 epoch 12.15M 6.70G 523 1.150 0.6803 1.072 model | log
HorNet 50 epoch 12.42M 6.84G 517 1.201 0.6906 1.096 model | log
MogaNet 50 epoch 12.76M 7.01G 416 1.152 0.6665 1.073 model | log
TAU 50 epoch 12.22M 6.70G 511 1.162 0.6707 1.078 model | log

STL Benchmarks on Temperature (r)

Method Setting Params FLOPs FPS MSE MAE RMSE Download
ConvLSTM 50 epoch 14.98M 136G 46 35.146 4.012 5.928 model | log
E3D-LSTM 50 epoch 51.09M 169G 35 36.534 4.100 6.044 model | log
PhyDNet 50 epoch 3.09M 36.8G 177 239.00 8.975 15.46 model | log
PredRNN 50 epoch 23.57M 278G 22 37.611 4.096 6.133 model | log
PredRNN++ 50 epoch 38.31M 413G 15 35.146 4.012 5.928 model | log
MIM 50 epoch 37.75M 109G 126 36.534 4.100 6.044 model | log
MAU 50 epoch 5.46M 39.6G 237 34.529 4.004 5.876 model | log
PredRNNv2 50 epoch 23.59M 279G 22 36.508 4.087 6.042 model | log
IncepU (SimVPv1) 50 epoch 14.67M 8.03G 160 34.355 3.994 5.861 model | log
gSTA (SimVPv2) 50 epoch 12.76M 7.01G 504 31.426 3.765 5.606 model | log
ViT 50 epoch 12.41M 7.99G 432 32.616 3.852 5.711 model | log
Swin Transformer 50 epoch 12.42M 6.88G 581 31.332 3.776 5.597 model | log
Uniformer 50 epoch 12.02M 7.45G 465 32.199 3.864 5.674 model | log
MLP-Mixer 50 epoch 11.10M 5.92G 713 34.467 3.950 5.871 model | log
ConvMixer 50 epoch 1.13M 0.95G 1705 32.829 3.909 5.730 model | log
Poolformer 50 epoch 9.98M 5.61G 722 31.989 3.803 5.656 model | log
ConvNeXt 50 epoch 10.09M 5.66G 689 33.179 3.928 5.760 model | log
VAN 50 epoch 12.15M 6.70G 523 31.712 3.812 5.631 model | log
HorNet 50 epoch 12.42M 6.84G 517 32.081 3.826 5.664 model | log
MogaNet 50 epoch 12.76M 7.01G 416 31.795 3.816 5.639 model | log
TAU 50 epoch 12.22M 6.70G 511 31.831 3.818 5.642 model | log

STL Benchmarks on Temperature (uv10)

Method Setting Params FLOPs FPS MSE MAE RMSE Download
ConvLSTM 50 epoch 14.98M 136G 43 1.8976 0.9215 1.3775 model | log
E3D-LSTM 50 epoch 51.81M 171G 35 2.4111 1.0342 1.5528 model | log
PhyDNet 50 epoch 3.09M 36.8G 172 16.798 2.9208 4.0986 model | log
PredRNN 50 epoch 23.65M 279G 21 1.8810 0.9068 1.3715 model | log
PredRNN++ 50 epoch 38.40M 414G 14 1.8727 0.9019 1.3685 model | log
MIM 50 epoch 37.75M 109G 122 3.1399 1.1837 1.7720 model | log
MAU 50 epoch 5.46M 39.6G 233 1.9001 0.9194 1.3784 model | log
PredRNNv2 50 epoch 23.68M 280G 21 2.0072 0.9413 1.4168 model | log
IncepU (SimVPv1) 50 epoch 14.67M 8.04G 154 1.9993 0.9510 1.4140 model | log
gSTA (SimVPv2) 50 epoch 12.76M 7.02G 498 1.5069 0.8142 1.2276 model | log
ViT 50 epoch 12.42M 8.0G 427 1.6262 0.8438 1.2752 model | log
Swin Transformer 50 epoch 12.42M 6.89G 577 1.4996 0.8145 1.2246 model | log
Uniformer 50 epoch 12.03M 7.46G 459 1.4850 0.8085 1.2186 model | log
MLP-Mixer 50 epoch 11.10M 5.93G 707 1.6066 0.8395 1.2675 model | log
ConvMixer 50 epoch 1.14M 0.96G 1698 1.7067 0.8714 1.3064 model | log
Poolformer 50 epoch 9.99M 5.62G 717 1.6123 0.8410 1.2698 model | log
ConvNeXt 50 epoch 10.09M 5.67G 682 1.6914 0.8698 1.3006 model | log
VAN 50 epoch 12.15M 6.71G 520 1.5958 0.8371 1.2632 model | log
HorNet 50 epoch 12.42M 6.85G 513 1.5539 0.8254 1.2466 model | log
MogaNet 50 epoch 12.76M 7.01G 411 1.6072 0.8451 1.2678 model | log
TAU 50 epoch 12.22M 6.70G 505 1.5925 0.8426 1.2619 model | log

STL Benchmarks on Temperature (tcc)

Method Setting Params FLOPs FPS MSE MAE RMSE Download
ConvLSTM 50 epoch 14.98M 136G 46 0.04944 0.15419 0.22234 model | log
E3D-LSTM 50 epoch 51.09M 169G 35 0.05729 0.15293 0.23936 model | log
PhyDNet 50 epoch 3.09M 36.8G 172 0.09913 0.22614 0.31485 model | log
PredRNN 50 epoch 23.57M 278G 22 0.05504 0.15877 0.23461 model | log
PredRNN++ 50 epoch 38.31M 413G 15 0.05479 0.15435 0.23407 model | log
MIM 50 epoch 37.75M 109G 126 0.05729 0.15293 0.23936 model | log
MAU 50 epoch 5.46M 39.6G 237 0.04955 0.15158 0.22260 model | log
PredRNNv2 50 epoch 23.59M 279G 22 0.05051 0.15867 0.22475 model | log
IncepU (SimVPv1) 50 epoch 14.67M 8.03G 160 0.04765 0.15029 0.21829 model | log
gSTA (SimVPv2) 50 epoch 12.76M 7.01G 504 0.04657 0.14688 0.21580 model | log
ViT 50 epoch 12.41M 7.99G 432 0.04778 0.15026 0.21859 model | log
Swin Transformer 50 epoch 12.42M 6.88G 581 0.04639 0.14729 0.21539 model | log
Uniformer 50 epoch 12.02M 7.45G 465 0.04680 0.14777 0.21634 model | log
MLP-Mixer 50 epoch 11.10M 5.92G 713 0.04925 0.15264 0.22192 model | log
ConvMixer 50 epoch 1.13M 0.95G 1705 0.04717 0.14874 0.21718 model | log
Poolformer 50 epoch 9.98M 5.61G 722 0.04694 0.14884 0.21667 model | log
ConvNeXt 50 epoch 10.09M 5.66G 689 0.04742 0.14867 0.21775 model | log
VAN 50 epoch 12.15M 6.70G 523 0.04694 0.14725 0.21665 model | log
HorNet 50 epoch 12.42M 6.84G 517 0.04692 0.14751 0.21661 model | log
MogaNet 50 epoch 12.76M 7.01G 416 0.04699 0.14802 0.21676 model | log
TAU 50 epoch 12.22M 6.70G 511 0.04723 0.14604 0.21733 model | log
Assets 170
Loading