def objective(trial):
# Data Augmentation
apply_tfms = trial.suggest_categorical("apply_tfms", [True, False])
if apply_tfms:
# MNIST is a hand-written digit dataset. Thus horizontal and vertical flipping are
# disabled. However, the two flipping will be important when the dataset is CIFAR or
# ImageNet.
tfms = aug_transforms(
do_flip=False,
flip_vert=False,
max_rotate=trial.suggest_int("max_rotate", 0, 45),
max_zoom=trial.suggest_float("max_zoom", 1, 2),
p_affine=trial.suggest_float("p_affine", 0.1, 1.0, step=0.1),
)
data = ImageDataLoaders.from_folder(
path, bs=BATCHSIZE, batch_tfms=tfms if apply_tfms else None
)
n_layers = trial.suggest_int("n_layers", 2, 5)
n_channels = [3]
for i in range(n_layers):
out_channels = trial.suggest_int("n_channels_{}".format(i), 3, 32)
n_channels.append(out_channels)
n_channels.append(2)
model = SimpleCNN(n_channels)
learn = Learner(
data,
model,
metrics=[accuracy],
# You could as FastAIPruningCallback in the fit function
cbs=FastAIPruningCallback(trial),
)
# See https://forums.fast.ai/t/how-to-diable-progress-bar-completely/65249/3
# to disable progress bar and logging info
with learn.no_bar():
with learn.no_logging():
learn.fit(EPOCHS)
return learn.validate()[-1]
def fetch(cls, df, imagesize: int, batchsize: int):
"""
Function to create a dataloader with the required transformations
"""
device = cls._detect_device(cls.SEED)
# We apply the following augmentations:
# - Flip the images vertically
# - Rotate the images randomly, with max rotation angle as 10 degres
# - Zoom in and out of the image, with max zoom as 1.1x
# - Change lighting of the image by 20%
# - Add warping to the image
# - Resize the image to given size. Typically, this is 224x224 and 320x320
# - Perform affine transformations on the image with probability 0.7
# - Perform lighing transformation on the image with probability 0.9
trfm = aug_transforms(
do_flip=True,
flip_vert=True,
max_rotate=10.0,
max_zoom=1.1,
max_lighting=0.2,
max_warp=0.2,
size=imagesize,
p_affine=0.7,
p_lighting=0.9,
)
# Change valid_pct to use a validation set and measure progress
image_loader = ImageDataLoaders.from_df(
df[["name", "label"]],
valid_pct=0.0,
seed=cls.SEED,
device=device,
item_tfms=Resize(460),
bs=batchsize,
batch_tfms=trfm,
)
return image_loader
writer.add_figure('Sample results', fig, step)
# ## Test
# ## TensorBoardCallback
# +
path = untar_data(URLs.PETS)
db = DataBlock(blocks=(ImageBlock, CategoryBlock),
get_items=get_image_files,
item_tfms=Resize(128),
splitter=RandomSubsetSplitter(train_sz=0.1, valid_sz=0.01),
batch_tfms=aug_transforms(size=64),
get_y=using_attr(RegexLabeller(r'(.+)_\d+.*$'), 'name'))
dls = db.dataloaders(path / 'images')
# -
learn = cnn_learner(dls, resnet18, metrics=accuracy)
learn.unfreeze()
learn.fit_one_cycle(3, cbs=TensorBoardCallback(Path.home() / 'tmp' / 'runs' / 'tb', trace_model=True))
# ## Projector
# ### Projector in TensorBoardCallback
path = untar_data(URLs.PETS)
def get_y_from_df(fname):
"""
根据名字从df中找到label
:param fname: 某张图像的绝对路径
:return: csv中对称性
"""
fname = path.basename(fname)
return df[df.img_name==fname]['label'].values[0]
data_block_512 = DataBlock(blocks = (ImageBlock, CategoryBlock, RegressionBlock),
get_items = get_image_files,
get_y = [get_y_from_name, get_y_from_df],
n_inp = 1,
item_tfms = Resize(512),
batch_tfms = aug_transforms(batch=True)
)
data_block_224 = DataBlock(blocks = (ImageBlock, CategoryBlock, RegressionBlock),
get_items = get_image_files,
get_y = [get_y_from_name, get_y_from_df],
n_inp = 1,
item_tfms = Resize(224),
batch_tfms = aug_transforms(batch=True)
)
data_block_312 = DataBlock(blocks = (ImageBlock, CategoryBlock, RegressionBlock),
get_items = get_image_files,
get_y = [get_y_from_name, get_y_from_df],
n_inp = 1,
item_tfms = [Resize(312)],