| 1 |
""" |
| 2 |
Example of defining a custom (image) transform using FFCV. |
| 3 |
For tutorial, see https://docs.ffcv.io/ffcv_examples/transform_with_inds.html. |
| 4 |
|
| 5 |
""" |
| 6 |
from dataclasses import replace |
| 7 |
import time |
| 8 |
from typing import Callable, Optional, Tuple |
| 9 |
import numpy as np |
| 10 |
import torchvision |
| 11 |
|
| 12 |
from ffcv.fields import IntField, RGBImageField |
| 13 |
from ffcv.fields.decoders import IntDecoder |
| 14 |
from ffcv.loader import Loader, OrderOption |
| 15 |
from ffcv.pipeline.compiler import Compiler |
| 16 |
from ffcv.pipeline.operation import Operation, AllocationQuery |
| 17 |
from ffcv.pipeline.state import State |
| 18 |
from ffcv.transforms import ToTensor |
| 19 |
from ffcv.writer import DatasetWriter |
| 20 |
|
| 21 |
|
| 22 |
class CorruptFixedLabels(Operation): |
| 23 |
def generate_code(self) -> Callable: |
| 24 |
# dst will be None since we don't ask for an allocation |
| 25 |
parallel_range = Compiler.get_iterator() |
| 26 |
def corrupt_fixed(labs, _, inds): |
| 27 |
for i in parallel_range(labs.shape[0]): |
| 28 |
# Because the random seed is tied to the image index, the |
| 29 |
# same images will be corrupted every epoch: |
| 30 |
np.random.seed(inds[i]) |
| 31 |
if np.random.rand() < 0.2: |
| 32 |
# They will also be corrupted to a deterministic label: |
| 33 |
labs[i] = np.random.randint(low=0, high=10) |
| 34 |
return labs |
| 35 |
|
| 36 |
corrupt_fixed.is_parallel = True |
| 37 |
corrupt_fixed.with_indices = True |
| 38 |
return corrupt_fixed |
| 39 |
|
| 40 |
def declare_state_and_memory(self, previous_state: State) -> Tuple[State, Optional[AllocationQuery]]: |
| 41 |
# No updates to state or extra memory necessary! |
| 42 |
return previous_state, None |
| 43 |
|
| 44 |
# Step 1: Create an FFCV-compatible CIFAR-10 dataset |
| 45 |
ds = torchvision.datasets.CIFAR10('/tmp', train=True, download=True) |
| 46 |
writer = DatasetWriter('/tmp/cifar.beton', { |
| 47 |
'image': RGBImageField(), |
| 48 |
'label': IntField() |
| 49 |
}) |
| 50 |
writer.from_indexed_dataset(ds) |
| 51 |
|
| 52 |
# Step 2: Create data loaders |
| 53 |
BATCH_SIZE = 512 |
| 54 |
label_pipelines = { |
| 55 |
'with': [IntDecoder(), CorruptFixedLabels(), ToTensor()], |
| 56 |
'without': [IntDecoder(), ToTensor()] |
| 57 |
} |
| 58 |
|
| 59 |
for name, pipeline in label_pipelines.items(): |
| 60 |
# Use SEQUENTIAL ordering to compare labels. |
| 61 |
loader = Loader(f'/tmp/cifar.beton', batch_size=BATCH_SIZE, |
| 62 |
num_workers=8, order=OrderOption.SEQUENTIAL, |
| 63 |
drop_last=True, pipelines={'label': pipeline}) |
| 64 |
|
| 65 |
# First epoch includes compilation time |
| 66 |
for ims, labs in loader: pass |
| 67 |
start_time = time.time() |
| 68 |
for ep in range(20): |
| 69 |
for i, (ims, labs) in enumerate(loader): |
| 70 |
if i == 0: # Inspect first batch |
| 71 |
print(f'> Labels (epoch {ep:2}): {labs[:40,0].tolist()}') |
| 72 |
print(f'Method: {name} | Shape: {ims.shape} | Time per epoch: {(time.time() - start_time) / 100:.5f}s') |