|
| 1 | +""" |
| 2 | +Remember to parameterize the file paths eventually |
| 3 | +""" |
| 4 | +import os |
| 5 | + |
| 6 | +import numpy as np |
| 7 | +from paddle.io import DataLoader |
| 8 | +from paddle.io import Dataset |
| 9 | +from paddle.io import DistributedBatchSampler |
| 10 | +from paddle.io import RandomSampler |
| 11 | + |
| 12 | +from .hdf5_datasets import DiffRe2DDataset |
| 13 | +from .hdf5_datasets import IncompNSDataset |
| 14 | +from .masking_generator import TubeMaskingGenerator |
| 15 | +from .mixed_dset_sampler import MultisetSampler |
| 16 | + |
| 17 | +broken_paths = [] |
| 18 | +# IF YOU ADD A NEW DSET MAKE SURE TO UPDATE THIS MAPPING SO MIXED DSET KNOWS HOW TO USE IT |
| 19 | +DSET_NAME_TO_OBJECT = { |
| 20 | + "incompNS": IncompNSDataset, |
| 21 | + "diffre2d": DiffRe2DDataset, |
| 22 | +} |
| 23 | + |
| 24 | + |
| 25 | +def get_data_loader(params, paths, distributed, split="train", rank=0, train_offset=0): |
| 26 | + # paths, types, include_string = zip(*paths) |
| 27 | + train_val_test = params.train_val_test |
| 28 | + if split == "pretrain": |
| 29 | + train_val_test = [ |
| 30 | + params.train_val_test[0] * params.pretrain_train[0], |
| 31 | + train_val_test[1], |
| 32 | + train_val_test[2], |
| 33 | + ] |
| 34 | + split = "train" # then restore to train split |
| 35 | + elif split == "train": |
| 36 | + # negative means reverse indexing |
| 37 | + train_val_test = [ |
| 38 | + -params.train_val_test[0] |
| 39 | + * params.pretrain_train[1] |
| 40 | + * params.train_subsample, |
| 41 | + train_val_test[1], |
| 42 | + train_val_test[2], |
| 43 | + ] |
| 44 | + dataset = MixedDataset( |
| 45 | + paths, |
| 46 | + n_steps=params.n_steps, |
| 47 | + train_val_test=train_val_test, |
| 48 | + split=split, |
| 49 | + tie_fields=params.tie_fields, |
| 50 | + use_all_fields=params.use_all_fields, |
| 51 | + enforce_max_steps=params.enforce_max_steps, |
| 52 | + train_offset=train_offset, |
| 53 | + masking=params.masking if hasattr(params, "masking") else None, |
| 54 | + blur=params.blur if hasattr(params, "blur") else None, |
| 55 | + rollout=getattr(params, "rollout", 1), |
| 56 | + ) |
| 57 | + # dataset = IncompNSDataset(paths[0], n_steps=params.n_steps, train_val_test=params.train_val_test, split=split) |
| 58 | + if distributed: |
| 59 | + base_sampler = DistributedBatchSampler |
| 60 | + else: |
| 61 | + base_sampler = RandomSampler |
| 62 | + sampler = MultisetSampler( |
| 63 | + dataset, |
| 64 | + base_sampler, |
| 65 | + params.batch_size, |
| 66 | + distributed=distributed, |
| 67 | + max_samples=params.epoch_size, |
| 68 | + rank=rank, |
| 69 | + ) # , seed=seed) |
| 70 | + # sampler = DistributedBatchSampler(dataset) if distributed else None |
| 71 | + dataloader = DataLoader( |
| 72 | + dataset, |
| 73 | + batch_size=int(params.batch_size), |
| 74 | + num_workers=params.num_data_workers, |
| 75 | + shuffle=False, # (sampler is None), |
| 76 | + drop_last=True, |
| 77 | + ) |
| 78 | + return dataloader, dataset, sampler |
| 79 | + |
| 80 | + |
| 81 | +class MixedDataset(Dataset): |
| 82 | + def __init__( |
| 83 | + self, |
| 84 | + path_list=[], |
| 85 | + n_steps=1, |
| 86 | + dt=1, |
| 87 | + train_val_test=(0.8, 0.1, 0.1), |
| 88 | + split="train", |
| 89 | + tie_fields=True, |
| 90 | + use_all_fields=True, |
| 91 | + extended_names=False, |
| 92 | + enforce_max_steps=False, |
| 93 | + train_offset=0, |
| 94 | + masking=None, |
| 95 | + blur=None, |
| 96 | + rollout=1, |
| 97 | + ): |
| 98 | + super().__init__() |
| 99 | + # Global dicts used by Mixed DSET. |
| 100 | + self.train_offset = train_offset |
| 101 | + self.path_list, self.type_list, self.include_string = zip(*path_list) |
| 102 | + self.tie_fields = tie_fields |
| 103 | + self.extended_names = extended_names |
| 104 | + self.split = split |
| 105 | + self.sub_dsets = [] |
| 106 | + self.offsets = [0] |
| 107 | + self.train_val_test = train_val_test |
| 108 | + self.use_all_fields = use_all_fields |
| 109 | + self.rollout = rollout |
| 110 | + |
| 111 | + for dset, path, include_string in zip( |
| 112 | + self.type_list, self.path_list, self.include_string |
| 113 | + ): |
| 114 | + subdset = DSET_NAME_TO_OBJECT[dset]( |
| 115 | + path, |
| 116 | + include_string, |
| 117 | + n_steps=n_steps, |
| 118 | + dt=dt, |
| 119 | + train_val_test=train_val_test, |
| 120 | + split=split, |
| 121 | + rollout=self.rollout, |
| 122 | + ) |
| 123 | + # Check to make sure our dataset actually exists with these settings |
| 124 | + try: |
| 125 | + len(subdset) |
| 126 | + except ValueError: |
| 127 | + raise ValueError( |
| 128 | + f"Dataset {path} is empty. Check that n_steps < trajectory_length in file." |
| 129 | + ) |
| 130 | + self.sub_dsets.append(subdset) |
| 131 | + self.offsets.append(self.offsets[-1] + len(self.sub_dsets[-1])) |
| 132 | + self.offsets[0] = -1 |
| 133 | + |
| 134 | + self.subset_dict = self._build_subset_dict() |
| 135 | + |
| 136 | + self.masking = masking # None or ((#frames, height, width), mask_ratio) |
| 137 | + if ( |
| 138 | + self.masking |
| 139 | + and type(self.masking) in [tuple, list] |
| 140 | + and len(self.masking) == 2 |
| 141 | + ): # and self.masking[1] > 0.: |
| 142 | + self.mask_generator = TubeMaskingGenerator(self.masking[0], self.masking[1]) |
| 143 | + self.blur = blur |
| 144 | + |
| 145 | + def get_state_names(self): |
| 146 | + name_list = [] |
| 147 | + if self.use_all_fields: |
| 148 | + for name, dset in DSET_NAME_TO_OBJECT.items(): |
| 149 | + field_names = dset._specifics()[2] |
| 150 | + name_list += field_names |
| 151 | + return name_list |
| 152 | + else: |
| 153 | + visited = set() |
| 154 | + for dset in self.sub_dsets: |
| 155 | + name = dset.get_name() # Could use extended names here |
| 156 | + if name not in visited: |
| 157 | + visited.add(name) |
| 158 | + name_list.append(dset.field_names) |
| 159 | + return [f for fl in name_list for f in fl] # Flatten the names |
| 160 | + |
| 161 | + def _build_subset_dict(self): |
| 162 | + # Maps fields to subsets of variables |
| 163 | + if self.tie_fields: # Hardcoded, but seems less effective anyway |
| 164 | + subset_dict = { |
| 165 | + "swe": [3], |
| 166 | + "incompNS": [0, 1, 2], |
| 167 | + "compNS": [0, 1, 2, 3], |
| 168 | + "diffre2d": [4, 5], |
| 169 | + } |
| 170 | + elif self.use_all_fields: |
| 171 | + cur_max = 0 |
| 172 | + subset_dict = {} |
| 173 | + for name, dset in DSET_NAME_TO_OBJECT.items(): |
| 174 | + field_names = dset._specifics()[2] |
| 175 | + subset_dict[name] = list(range(cur_max, cur_max + len(field_names))) |
| 176 | + cur_max += len(field_names) |
| 177 | + else: |
| 178 | + subset_dict = {} |
| 179 | + cur_max = self.train_offset |
| 180 | + for dset in self.sub_dsets: |
| 181 | + name = dset.get_name(self.extended_names) |
| 182 | + if name not in subset_dict: |
| 183 | + subset_dict[name] = list( |
| 184 | + range(cur_max, cur_max + len(dset.field_names)) |
| 185 | + ) |
| 186 | + cur_max += len(dset.field_names) |
| 187 | + return subset_dict |
| 188 | + |
| 189 | + def __getitem__(self, index): |
| 190 | + file_idx = ( |
| 191 | + np.searchsorted(self.offsets, index, side="right") - 1 |
| 192 | + ) # which dataset are we are on |
| 193 | + local_idx = index - max(self.offsets[file_idx], 0) |
| 194 | + |
| 195 | + x, y = self.sub_dsets[file_idx][local_idx] |
| 196 | + try: |
| 197 | + x, y = self.sub_dsets[file_idx][local_idx] |
| 198 | + except: # noqa |
| 199 | + print( |
| 200 | + "FAILED AT ", file_idx, local_idx, index, int(os.environ.get("RANK", 0)) |
| 201 | + ) |
| 202 | + |
| 203 | + if ( |
| 204 | + self.masking |
| 205 | + and type(self.masking) in [tuple, list] |
| 206 | + and len(self.masking) == 2 |
| 207 | + ): # and self.masking[1] > 0.: |
| 208 | + mask = self.mask_generator() |
| 209 | + # return x, file_idx, paddle.to_tensor(self.subset_dict[self.sub_dsets[file_idx].get_name()]), bcs, y, mask, x_blur |
| 210 | + return x, y, mask |
| 211 | + else: |
| 212 | + return x, y |
| 213 | + |
| 214 | + def __len__(self): |
| 215 | + return sum([len(dset) for dset in self.sub_dsets]) |
0 commit comments