def __init__(self,
mode,
batch_size=256,
shuffle=False,
num_workers=25,
cache=50000,
collate_fn=default_collate,
drop_last=False,
cuda=False):
# enumerate standard imagenet augmentors
imagenet_augmentors = fbresnet_augmentor(mode == 'train')
# load the lmdb if we can find it
lmdb_loc = os.path.join(os.environ['IMAGENET'],
'ILSVRC-%s.lmdb' % mode)
ds = td.LMDBData(lmdb_loc, shuffle=False)
ds = td.LocallyShuffleData(ds, cache)
ds = td.PrefetchData(ds, 5000, 1)
ds = td.LMDBDataPoint(ds)
ds = td.MapDataComponent(ds,
lambda x: cv2.imdecode(x, cv2.IMREAD_COLOR),
0)
ds = td.AugmentImageComponent(ds, imagenet_augmentors)
ds = td.PrefetchDataZMQ(ds, num_workers)
self.ds = td.BatchData(ds, batch_size)
self.ds.reset_state()
self.batch_size = batch_size
self.num_workers = num_workers
self.cuda = cuda
def __init__(self,
mode,
batch_size=256,
shuffle=False,
num_workers=25,
cache=50000,
collate_fn=default_collate,
remainder=False,
cuda=False,
transform=None):
# enumerate standard imagenet augmentors
#imagenet_augmentors = fbresnet_augmentor(mode == 'train')
imagenet_augmentors = [ImgAugTVCompose(transform)]
# load the lmdb if we can find it
lmdb_loc = os.path.join(os.environ['IMAGENET'],
'ILSVRC-%s.lmdb' % mode)
ds = td.LMDBData(lmdb_loc, shuffle=False)
if mode == 'train':
ds = td.LocallyShuffleData(ds, cache)
ds = td.PrefetchData(ds, 5000, 1)
ds = td.LMDBDataPoint(ds)
#ds = td.MapDataComponent(ds, lambda x: cv2.imdecode(x, cv2.IMREAD_COLOR), 0)
ds = td.MapDataComponent(
ds, lambda x: np.asarray(Image.open(io.BytesIO(x)).convert('RGB')),
0)
ds = td.AugmentImageComponent(ds, imagenet_augmentors)
ds = td.PrefetchDataZMQ(ds, num_workers)
self.ds = td.BatchData(ds, batch_size, remainder=remainder)
self.ds.reset_state()
self.batch_size = batch_size
self.num_workers = num_workers
self.cuda = cuda
def __init__(self,
mode,
do_aug,
batch_size=256,
shuffle=False,
num_workers=25,
cache=50000,
cuda=False,
out_tensor=True,
data_transforms=None):
# enumerate standard imagenet augmentors
imagenet_augmentors = fbresnet_augmentor(do_aug)
# load the lmdb if we can find it
lmdb_loc = os.path.join(os.environ['IMAGENET'],
'ILSVRC-%s.lmdb' % mode)
ds = td.LMDBSerializer.load(lmdb_loc, shuffle=shuffle)
#ds = td.LMDBData(lmdb_loc, shuffle=False)
#ds = td.LocallyShuffleData(ds, cache)
#ds = td.PrefetchData(ds, 5000, 1)
#ds = td.LMDBDataPoint(ds)
ds = td.MapDataComponent(
ds, lambda x: cv2.imdecode(x, cv2.IMREAD_COLOR)[:, :, ::-1], 0)
ds = td.AugmentImageComponent(ds, imagenet_augmentors)
ds = td.MultiProcessRunnerZMQ(ds, num_workers)
self.ds = td.BatchData(ds, batch_size)
self.ds.reset_state()
self.batch_size = batch_size
self.num_workers = num_workers
self.cuda = cuda
self.out_tensor = out_tensor
# data_transforms should be present only when out_tensor=True
# data_transforms typically consists of
# PIL Image transforms, ToTensor(), Normalize():
# normalize = transforms.Compose( [
# transforms.ToTensor(),
# transforms.Normalize(mean=[0.485, 0.456, 0.406],
# std=[0.229, 0.224, 0.225]) ] )
self.data_transforms = data_transforms
print("Loaded '%s'." % lmdb_loc)
def plate_generator_pipline(pg, num_proc=10):
augmentors = df.imgaug.AugmentorList([
df.imgaug.RandomOrderAug([
df.imgaug.BrightnessScale((0.6, 1.4), clip=False),
df.imgaug.Contrast((0.6, 1.4), clip=False),
df.imgaug.Saturation(0.4, rgb=False),
# rgb-bgr conversion for the constants copied from fb.resnet.torch
df.imgaug.Lighting(
std=0.1,
eigval=np.asarray([0.2175, 0.0188, 0.0045][::-1]) * 255.0,
eigvec=np.array(
[[-0.5675, 0.7192, 0.4009], [-0.5808, -0.0045, -0.8140],
[-0.5836, -0.6948, 0.4203]],
dtype='float32')[::-1, ::-1])
]),
df.imgaug.RandomOrderAug([
df.imgaug.RandomApplyAug(df.imgaug.GaussianNoise(45), 0.5),
df.imgaug.RandomApplyAug(df.imgaug.GaussianBlur(), 0.5),
df.imgaug.RandomApplyAug(df.imgaug.JpegNoise(), 0.5),
# # df.imgaug.RandomApplyAug(df.imgaug.Grayscale(keepshape=True), 0.2),
df.imgaug.RandomApplyAug(df.imgaug.SaltPepperNoise(), 0.5),
df.imgaug.RandomApplyAug(MotionBlur(15), 1.0),
]),
df.imgaug.RandomOrderAug([
df.imgaug.RandomApplyAug(
df.imgaug.Affine(scale=(0.8, 1.0),
translate_frac=(0.05, 0.05),
rotate_max_deg=10,
shear=35), 0.5),
]),
])
ds = df.DataFromGenerator(pg)
ds = df.AugmentImageComponent(ds, augmentors)
# ds = df.MultiProcessRunnerZMQ(ds, num_proc=num_proc)
return ds
import tensorpack.dataflow as df
if __name__ == '__main__':
ds = df.dataset.Mnist('train')
augmentors = [
df.imgaug.RandomApplyAug(
df.imgaug.RandomResize((0.8, 1.2), (0.8, 1.2)), 0.3),
df.imgaug.RandomApplyAug(df.imgaug.RotationAndCropValid(15), 0.5),
df.imgaug.RandomApplyAug(
df.imgaug.SaltPepperNoise(white_prob=0.01, black_prob=0.01), 0.25),
df.imgaug.Resize((28, 28)),
df.imgaug.CenterPaste((32, 32)),
df.imgaug.RandomCrop((28, 28)),
df.imgaug.MapImage(lambda x: x.reshape(28, 28, 1))
]
ds = df.AugmentImageComponent(ds, augmentors)
ds = df.BatchData(ds, batch_size=32, remainder=False)
ds = df.PrefetchData(ds, nr_prefetch=12, nr_proc=2)
ds = df.PrintData(ds)
df.send_dataflow_zmq(ds, 'tcp://localhost:2222')
import tensorflow as tf
import tensorpack.dataflow as df
if __name__ == '__main__':
# prepare dataset
ds = df.dataset.Mnist('train')
augmentors_variation = [
df.imgaug.Resize((28, 28)),
df.imgaug.CenterPaste((32, 32)),
df.imgaug.RandomCrop((28, 28)),
df.imgaug.MapImage(lambda v: v.reshape(784))
]
ds = df.AugmentImageComponent(ds, augmentors_variation)
ds = df.PrefetchData(ds, nr_prefetch=12, nr_proc=4)
ds = df.BatchData(ds, batch_size=128, remainder=False, use_list=False)
# create the model
x = tf.placeholder(tf.float32, [None, 784])
W = tf.Variable(tf.ones([784, 10]))
b = tf.Variable(tf.zeros([10]))
y = tf.matmul(x, W) + b
y_ = tf.placeholder(tf.int64, [None])
cross_entropy = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y_, logits=y))
global_step = tf.train.get_or_create_global_step()
train_op = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(
cross_entropy, global_step=global_step)
correct_prediction = tf.equal(tf.argmax(y, 1), y_)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
else:
logging.basicConfig(level=logging.INFO,
format='[%(asctime)s %(levelname)s] %(message)s',
filename=args.log_filename)
if args.augment:
augmentors = fbresnet_augmentor(isTrain=True)
else:
augmentors = [
df.imgaug.Resize((128, 128)),
]
ds = dataflow.dataset.ILSVRC12(
args.service_code, 'train',
shuffle=True).parallel(num_threads=args.threads)
ds = df.AugmentImageComponent(ds, augmentors, copy=False)
ds = df.PrefetchDataZMQ(ds, nr_proc=args.process)
if args.view:
ds = dataflow.utils.image.Viewer(ds,
lambda x: x[1] == 4,
'label-4',
prob=1.0,
pos=(0, (128 + 64) * 0))
ds = dataflow.utils.image.Viewer(ds,
lambda x: x[1] == 16,
'label-16',
prob=1.0,
pos=(0, (128 + 64) * 1))
ds = dataflow.utils.image.Viewer(ds,
lambda x: x[1] == 32,
'label-32',
df.imgaug.RandomOrderAug([
df.imgaug.RandomApplyAug(
df.imgaug.BrightnessScale((0.8, 1.2), clip=False), 0.5),
df.imgaug.RandomApplyAug(
df.imgaug.Contrast((0.8, 1.2), clip=False), 0.5),
# df.imgaug.RandomApplyAug(df.imgaug.Saturation(0.4, rgb=False), 0.5),
]),
]
augmentors_default = [
df.imgaug.Resize((32, 32)),
df.imgaug.MapImage(lambda x: x.reshape(32, 32, 1))
]
# keep original image at index 1
ds = df.MapData(
ds, lambda datapoint: [datapoint[0], datapoint[0]] + datapoint[1:])
ds = df.AugmentImageComponent(ds,
augmentors_variation + augmentors_default)
ds = df.AugmentImageComponent(ds, augmentors_default, index=1)
ds = df.PrefetchData(ds, nr_prefetch=12, nr_proc=4)
ds = df.PrintData(ds)
ds = df.BatchData(ds, batch_size=32, remainder=False, use_list=True)
ds = df.PrintData(ds)
for minibatch in ds.get_data():
images, originals, labels = minibatch
image, original, label = images[0], originals[0], labels[0]
name = '{:02d}'.format(label)
cv2.namedWindow(name)
cv2.moveWindow(name, 0, 25 + 128 * label)
display_image = np.concatenate((image, original), axis=1)
