Spaces:
Running on Zero
Running on Zero
File size: 7,646 Bytes
dcc4594 | 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 | import torch
import torchvision.datasets as datasets
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.data.distributed import DistributedSampler
import torch.distributed as dist
import time
import os
import numpy as np
import matplotlib.pyplot as plt
from torchvision.utils import make_grid
from datasets.datasets import PongDataset, SonicDataset, PolePositionDataset, PicoDoomDataset, ZeldaDataset
DEFAULT_NUM_WORKERS = 2
DEFAULT_PREFETCH_FACTOR = 2
DEFAULT_PIN_MEMORY = False
DEFAULT_PERSISTENT_WORKERS = True
def _default_video_transform():
return transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
def _load_video_dataset_pair(dataset_cls, video_rel_path, h5_rel_path, num_frames, transform=None, fps=30, preload_ratio=1, **kwargs):
current_folder_path = os.getcwd()
video_path = current_folder_path + video_rel_path
preprocessed_path = current_folder_path + h5_rel_path
transform = _default_video_transform() if transform is None else transform
train = dataset_cls(
video_path,
transform=transform,
save_path=preprocessed_path,
train=True,
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio,
**kwargs
)
val = dataset_cls(
video_path,
transform=transform,
save_path=preprocessed_path,
train=False,
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio,
**kwargs
)
return train, val
def load_pong(num_frames=1, fps=15, preload_ratio=1):
return _load_video_dataset_pair(
PongDataset,
'/data/pong.mp4',
'/data/pong_frames.h5',
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio
)
def load_sonic(num_frames=4, fps=15, preload_ratio=1):
return _load_video_dataset_pair(
SonicDataset,
'/data/sonic_frames.mp4',
'/data/sonic_frames.h5',
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio
)
def load_pole_position(num_frames=4, fps=15, preload_ratio=1):
return _load_video_dataset_pair(
PolePositionDataset,
'/data/pole_position.mp4',
'/data/pole_position_frames.h5',
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio
)
def load_picodoom(num_frames=4, fps=30, preload_ratio=1):
return _load_video_dataset_pair(
PicoDoomDataset,
'/data/picodoom cleaned.mp4',
'/data/picodoom_frames.h5',
num_frames=num_frames,
fps=30,
preload_ratio=preload_ratio
)
def load_zelda(num_frames=4, fps=15, preload_ratio=1):
return _load_video_dataset_pair(
ZeldaDataset,
'/data/Zelda oot2d 1 Cut.mp4',
'/data/zelda_frames.h5',
num_frames=num_frames,
fps=fps,
preload_ratio=preload_ratio
)
def data_loaders(train_data, val_data, batch_size, distributed=False, rank=0, world_size=1):
train_sampler = None
val_sampler = None
if distributed:
train_sampler = DistributedSampler(train_data, num_replicas=world_size, rank=rank, shuffle=True, drop_last=True)
val_sampler = DistributedSampler(val_data, num_replicas=world_size, rank=rank, shuffle=False, drop_last=True)
train_loader = DataLoader(
train_data,
batch_size=batch_size,
shuffle=False if train_sampler is not None else True,
sampler=train_sampler,
num_workers=DEFAULT_NUM_WORKERS,
pin_memory=DEFAULT_PIN_MEMORY,
persistent_workers=DEFAULT_PERSISTENT_WORKERS,
prefetch_factor=DEFAULT_PREFETCH_FACTOR,
drop_last=True
)
val_loader = DataLoader(
val_data,
batch_size=batch_size,
shuffle=False if val_sampler is not None else True,
sampler=val_sampler,
num_workers=DEFAULT_NUM_WORKERS,
pin_memory=DEFAULT_PIN_MEMORY,
persistent_workers=DEFAULT_PERSISTENT_WORKERS,
prefetch_factor=DEFAULT_PREFETCH_FACTOR,
drop_last=True
)
return train_loader, val_loader
def load_data_and_data_loaders(dataset, batch_size, num_frames=1, distributed=False, rank=0, world_size=1, fps=15, preload_ratio=1):
if dataset == 'PONG':
training_data, validation_data = load_pong(num_frames=num_frames, fps=fps, preload_ratio=preload_ratio)
elif dataset == 'SONIC':
training_data, validation_data = load_sonic(num_frames=num_frames, fps=fps, preload_ratio=preload_ratio)
elif dataset == 'POLE_POSITION':
training_data, validation_data = load_pole_position(num_frames=num_frames, fps=fps, preload_ratio=preload_ratio)
elif dataset == 'PICODOOM':
training_data, validation_data = load_picodoom(num_frames=num_frames, fps=fps, preload_ratio=preload_ratio)
elif dataset == 'ZELDA':
training_data, validation_data = load_zelda(num_frames=num_frames, fps=fps, preload_ratio=preload_ratio)
else:
raise ValueError('Invalid dataset')
training_loader, validation_loader = data_loaders(
training_data, validation_data, batch_size,
distributed=distributed, rank=rank, world_size=world_size
)
x_train_var = np.var(training_data.data)
return training_data, validation_data, training_loader, validation_loader, x_train_var
def readable_timestamp():
return time.ctime().replace(' ', ' ').replace(
' ', '_').replace(':', '_').lower()
def visualize_reconstruction(original, reconstruction, save_path=None):
# original: (B, C, H, W) or (B, T, C, H, W)
# reconstruction: (B, C, H, W) or (B, T, C, H, W)
# move tensors to CPU and convert to float32 for matplotlib compatibility
original = original.detach().to('cpu', dtype=torch.float32)
reconstruction = reconstruction.detach().to('cpu', dtype=torch.float32)
# handle single frames by expanding to sequences
if original.dim() == 4: # (B, C, H, W)
original = original.unsqueeze(1) # Add sequence dimension
if reconstruction.dim() == 4: # (B, C, H, W)
reconstruction = reconstruction.unsqueeze(1) # Add sequence dimension
# take first 4 sequences, each of length 4 (or available length)
num_sequences = min(4, original.shape[0])
seq_length = min(4, original.shape[1])
original = original[:num_sequences, :seq_length] # (B, T, C, H, W)
reconstruction = reconstruction[:num_sequences, :seq_length] # (B, T, C, H, W)
# create a figure with two subplots side by side
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(16, 8))
# for original sequences
# reshape to (B * T, C, H, W) for make_grid
orig_flat = original.reshape(-1, *original.shape[2:]) # (B*T, C, H, W)
grid_orig = make_grid(orig_flat, nrow=seq_length, normalize=True, padding=2).clamp(0, 1)
ax1.imshow(grid_orig.permute(1, 2, 0).contiguous().numpy())
ax1.axis('off')
ax1.set_title(f'Original Sequences (4 sequences × {seq_length} frames)')
# for reconstructed sequences
recon_flat = reconstruction.reshape(-1, *reconstruction.shape[2:]) # (B*T, C, H, W)
grid_recon = make_grid(recon_flat, nrow=seq_length, normalize=True, padding=2).clamp(0, 1)
ax2.imshow(grid_recon.permute(1, 2, 0).contiguous().numpy())
ax2.axis('off')
ax2.set_title(f'Reconstructed Sequences (4 sequences × {seq_length} frames)')
plt.tight_layout()
if save_path:
plt.savefig(save_path, dpi=150, bbox_inches='tight')
plt.close()
else:
plt.show()
plt.close()
|