File size: 4,249 Bytes
2862bae | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | model:
start_epoch: 0
max_epoch: 1
train_lr: 2.5E-4
finetune_lr: 1E-7
patch_size: [2, 4, 4]
embed_dim: 1536
num_groups: 32
num_heads: 8
window_size: 7
short_num_steps: 20
medium_num_steps: 40
long_num_steps: 60
finetune_step: 1
step_change_freq: 200
input_steps: 2
num_blocks: 8
checkpoint_dir : "./data/checkpoints"
patience: 50
# 整个数据读取流程
datapipe:
name: "ERA5"
task: "weather_forecasting"
# dataset设定
dataset:
type: "hdf5"
data_dir: './data/' # "$ONESCIENCE_DATASETS_DIR/ERA5/newh5/"
train_time: [2000,2001]
val_time: [2022]
test_time: [2023]
img_size: [2, 721, 1440]
verbose: true
cache: false
# 气象变量
channels: ['10m_u_component_of_wind', '10m_v_component_of_wind', '2m_temperature', 'mean_sea_level_pressure', 'total_precipitation',
'geopotential_50', 'geopotential_100', 'geopotential_150', 'geopotential_200', 'geopotential_250',
'geopotential_300', 'geopotential_400', 'geopotential_500', 'geopotential_600', 'geopotential_700',
'geopotential_850', 'geopotential_925', 'geopotential_1000',
'relative_humidity_50', 'relative_humidity_100', 'relative_humidity_150', 'relative_humidity_200', 'relative_humidity_250',
'relative_humidity_300', 'relative_humidity_400', 'relative_humidity_500', 'relative_humidity_600', 'relative_humidity_700',
'relative_humidity_850','relative_humidity_925', 'relative_humidity_1000',
'u_component_of_wind_50', 'u_component_of_wind_100', 'u_component_of_wind_150', 'u_component_of_wind_200', 'u_component_of_wind_250',
'u_component_of_wind_300', 'u_component_of_wind_400', 'u_component_of_wind_500', 'u_component_of_wind_600','u_component_of_wind_700',
'u_component_of_wind_850', 'u_component_of_wind_925', 'u_component_of_wind_1000',
'v_component_of_wind_50', 'v_component_of_wind_100', 'v_component_of_wind_150', 'v_component_of_wind_200', 'v_component_of_wind_250',
'v_component_of_wind_300', 'v_component_of_wind_400', 'v_component_of_wind_500', 'v_component_of_wind_600','v_component_of_wind_700',
'v_component_of_wind_850', 'v_component_of_wind_925', 'v_component_of_wind_1000',
'temperature_50', 'temperature_100', 'temperature_150', 'temperature_200', 'temperature_250',
'temperature_300', 'temperature_400', 'temperature_500', 'temperature_600', 'temperature_700',
'temperature_850', 'temperature_925', 'temperature_1000'
]
variables:
- "u10" # 10m U wind component
- "v10" # 10m V wind component
- "t2m" # 2m temperature
- "msl" # Mean sea level pressure
- "z500" # Geopotential at 500 hPa
- "t850" # Temperature at 850 hPa
# 时间配置
time_range: ["2000-01-01", "2020-12-31"]
time_steps: 1
time_res: 6
# 空间配置
spatial_resolution: [0.25, 0.25]
# 采样配置
num_samples: -1 # -1 表示使用全部数据
shuffle: true
random_seed: 42
# 领域特定配置
extra:
levels: [500, 850, 1000]
lat_range: [-90, 90]
lon_range: [0, 360]
# 数据转换配置
transforms:
- type: "Normalize"
params:
mean: [0.0, 0.0, 288.0, 101325.0, 50000.0, 270.0]
std: [5.0, 5.0, 15.0, 1000.0, 5000.0, 10.0]
keys: ["input", "target"]
- type: "ToTensor"
params:
keys: null # null表示转换所有numpy数组
# 其他配置
# DataLoader配置
dataloader:
mask_dtype: "float32"
batch_size: 1
num_workers: 1
pin_memory: true
drop_last: true
shuffle: false # 使用sampler时设为false
prefetch_factor: 2
persistent_workers: true
# 分布式配置
distributed:
enabled: true
sampler: "DistributedSampler"
rank: 0
world_size: 4
shuffle: true
seed: 42
drop_last: true
|