File size: 9,079 Bytes
3de4238 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 | import torch
import rich
import pickle
import numpy as np
def lengths_to_mask(lengths):
max_len = max(lengths)
mask = torch.arange(max_len, device=lengths.device).expand(
len(lengths), max_len) < lengths.unsqueeze(1)
return mask
# padding to max length in one batch
def collate_tensors(batch):
if isinstance(batch[0], np.ndarray):
batch = [torch.tensor(b).float() for b in batch]
dims = batch[0].dim()
max_size = [max([b.size(i) for b in batch]) for i in range(dims)]
size = (len(batch), ) + tuple(max_size)
canvas = batch[0].new_zeros(size=size)
for i, b in enumerate(batch):
sub_tensor = canvas[i]
for d in range(dims):
sub_tensor = sub_tensor.narrow(d, 0, b.size(d))
sub_tensor.add_(b)
return canvas
def humanml3d_collate(batch):
notnone_batches = [b for b in batch if b is not None]
EvalFlag = False if notnone_batches[0][5] is None else True
# Sort by text length
if EvalFlag:
notnone_batches.sort(key=lambda x: x[5], reverse=True)
# Motion only
adapted_batch = {
"motion":
collate_tensors([torch.tensor(b[1]).float() for b in notnone_batches]),
"length": [b[2] for b in notnone_batches],
}
# Text and motion
if notnone_batches[0][0] is not None:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"all_captions": [b[7] for b in notnone_batches],
})
# Evaluation related
if EvalFlag:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"word_embs":
collate_tensors(
[torch.tensor(b[3]).float() for b in notnone_batches]),
"pos_ohot":
collate_tensors(
[torch.tensor(b[4]).float() for b in notnone_batches]),
"text_len":
collate_tensors([torch.tensor(b[5]) for b in notnone_batches]),
"tokens": [b[6] for b in notnone_batches],
})
# Tasks
if len(notnone_batches[0]) == 9:
adapted_batch.update({"tasks": [b[8] for b in notnone_batches]})
return adapted_batch
def nymeria_collate_3dscene(batch):
notnone_batches = [b for b in batch if b is not None]
EvalFlag = False if notnone_batches[0][5] is None else True
# Sort by text length
if EvalFlag:
notnone_batches.sort(key=lambda x: x[5], reverse=True)
# Motion only
adapted_batch = {
"motion":
collate_tensors([torch.tensor(b[1], dtype=torch.float32) for b in notnone_batches]),
"length": [b[2] for b in notnone_batches],
}
# Text and motion
if notnone_batches[0][0] is not None:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"all_captions": [b[7] for b in notnone_batches],
"pc": collate_tensors([torch.as_tensor(b[9], dtype=torch.float32) for b in notnone_batches]),
"pc_embed": collate_tensors([torch.as_tensor(b[10], dtype=torch.float32) for b in notnone_batches]),
"pc_mask": collate_tensors([torch.as_tensor(b[11]).long() for b in notnone_batches]),
"pc_length": [b[12] for b in notnone_batches],
"three_points": collate_tensors([torch.as_tensor(b[13], dtype=torch.float32) for b in notnone_batches]),
"three_points_length": [b[14] for b in notnone_batches],
# "video_rgb": collate_tensors([torch.as_tensor(b[15]) for b in notnone_batches]),
"video_embed": collate_tensors([torch.as_tensor(b[15], dtype=torch.float32) for b in notnone_batches]),
"video_lengths": [b[16] for b in notnone_batches],
"future_text": [b[17] for b in notnone_batches],
"future_motion": collate_tensors([torch.as_tensor(b[18], dtype=torch.float32) for b in notnone_batches]),
"future_motion_length": [b[19] for b in notnone_batches],
"global_head_voxel": collate_tensors([torch.as_tensor(b[22], dtype=torch.float32) for b in notnone_batches]),
"global_head_rot": collate_tensors([torch.as_tensor(b[23], dtype=torch.float32) for b in notnone_batches]),
"min_coord": collate_tensors([torch.as_tensor(b[24], dtype=torch.float32) for b in notnone_batches]),
"obstacle_cot_answer": [b[25] for b in notnone_batches],
# "past_pose": collate_tensors([torch.as_tensor(b[20], dtype=torch.float32) for b in notnone_batches]),
# "fut_pose": collate_tensors([torch.as_tensor(b[21], dtype=torch.float32) for b in notnone_batches]),
})
# if len(notnone_batches[0]) > 25 :
# adapted_batch.update({
# "scene_question": [b[25] for b in notnone_batches],
# "scene_answer": [b[26] for b in notnone_batches],
# })
if not EvalFlag :
adapted_batch.update({
"past_pose": collate_tensors([torch.as_tensor(b[20], dtype=torch.float32) for b in notnone_batches]),
"fut_pose": collate_tensors([torch.as_tensor(b[21], dtype=torch.float32) for b in notnone_batches]),
})
# Evaluation related
if EvalFlag:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"word_embs":
collate_tensors(
[torch.tensor(b[3]).float() for b in notnone_batches]),
"pos_ohot":
collate_tensors(
[torch.tensor(b[4]).float() for b in notnone_batches]),
"text_len":
collate_tensors([torch.tensor(b[5]) for b in notnone_batches]),
"tokens": [b[6] for b in notnone_batches],
"scene_name": [b[26] for b in notnone_batches],
"data_idx": [b[27] for b in notnone_batches],
})
# Tasks
if notnone_batches[0][8] is not None:
# if len(notnone_batches[0]) == 9+2:
adapted_batch.update({"tasks": [b[8] for b in notnone_batches]})
return adapted_batch
def nymeria_collate_3dscene_pretrain(batch):
notnone_batches = [b for b in batch if b is not None]
EvalFlag = False if notnone_batches[0][5] is None else True
# Sort by text length
if EvalFlag:
notnone_batches.sort(key=lambda x: x[5], reverse=True)
# Motion only
adapted_batch = {
"motion":
collate_tensors([torch.tensor(b[1]).float() for b in notnone_batches]),
"length": [b[2] for b in notnone_batches],
}
# Text and motion
if notnone_batches[0][0] is not None:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"all_captions": [b[7] for b in notnone_batches],
})
# Text and scene
if notnone_batches[0][0] is not None:
adapted_batch.update({
"pc": collate_tensors([torch.as_tensor(b[9]) for b in notnone_batches]),
"pc_embed": collate_tensors([torch.as_tensor(b[10]).float() for b in notnone_batches]),
"pc_mask": collate_tensors([torch.as_tensor(b[11]).long() for b in notnone_batches]),
"pc_len": [b[12] for b in notnone_batches],
"video_embed": collate_tensors([torch.as_tensor(b[13]).float() for b in notnone_batches]),
"video_lengths": [b[14] for b in notnone_batches],
"scene_question": [b[15] for b in notnone_batches],
"scene_answer": [b[16] for b in notnone_batches],
"global_head_voxel": collate_tensors([torch.as_tensor(b[18], dtype=torch.float32) for b in notnone_batches]),
"global_head_rot": collate_tensors([torch.as_tensor(b[19], dtype=torch.float32) for b in notnone_batches]),
"min_coord": collate_tensors([torch.as_tensor(b[20], dtype=torch.float32) for b in notnone_batches]),
"obstacle_answer": [b[21] if len(b) > 21 else '' for b in notnone_batches],
})
if not EvalFlag :
adapted_batch.update({
"past_pose": collate_tensors([torch.as_tensor(b[17], dtype=torch.float32) for b in notnone_batches]),
})
# Evaluation related
if EvalFlag:
adapted_batch.update({
"text": [b[0] for b in notnone_batches],
"word_embs":
collate_tensors(
[torch.tensor(b[3]).float() for b in notnone_batches]),
"pos_ohot":
collate_tensors(
[torch.tensor(b[4]).float() for b in notnone_batches]),
"text_len":
collate_tensors([torch.tensor(b[5]) for b in notnone_batches]),
"tokens": [b[6] for b in notnone_batches],
})
# Tasks
if notnone_batches[0][8] is not None:
# if len(notnone_batches[0]) == 9+2:
adapted_batch.update({"tasks": [b[8] for b in notnone_batches]})
return adapted_batch
def load_pkl(path, description=None, progressBar=False):
if progressBar:
with rich.progress.open(path, 'rb', description=description) as file:
data = pickle.load(file)
else:
with open(path, 'rb') as file:
data = pickle.load(file)
return data
|