def __init__(self, image_size=(126, 32)):
self.image_size = image_size
self.background_blend = BackgroundBlend(
"/home/agarcia/repos/mafat-radar-challenge/mafat_radar_challenge/data/mafat_background_v9_spectrogram.npy",
alpha=0.8,
p=0.2,
)
self.gaussian_filter = GaussianFilter(kernel_size=(20, 1))
self.rolling_x = RollingX(shift=(-20, 20))
self.rolling_y = RollingY(shift=(-20, 20))
self.delta = Delta()
self.deltadelta = DeltaDelta()
self.background_supp = BackgroundSuppression()
self.freq_mask = FreqMask(F=(5, 25), num_masks=(1, 3))
self.time_mask = TimeMask(T=(1, 5), num_masks=(1, 10))
self.aug = Compose(
[
Lambda(self.rolling_x.transform),
Lambda(self.rolling_y.transform),
# Lambda(self.background_supp.transform), # Background suppresion
Lambda(minmax_norm), # This is needed for Noise and Blur addition
HorizontalFlip(p=0.5),
VerticalFlip(p=0.5),
Rotate(limit=(180, 180), p=0.5),
# ShiftScaleRotate(
# shift_limit=0.1,
# scale_limit=0,
# rotate_limit=0,
# p=0.5,
# border_mode=cv2.BORDER_CONSTANT,
# ),
# OneOf(
# [
# MultiplicativeNoise(
# multiplier=[0.8, 1.3], elementwise=True, p=0.25
# ),
# GaussianBlur(p=0.25, blur_limit=(1, 3)),
# ]
# ),
# RandomBrightnessContrast(
# brightness_limit=0.1, contrast_limit=0.1, p=0.1
# ),
# Cutout(
# num_holes=1,
# max_h_size=int(0.2 * self.image_size[0]),
# max_w_size=int(0.2 * self.image_size[1]),
# p=0.5,
# ),
# Lambda(self.delta.transform),
# Lambda(self.deltadelta.transform),
# Lambda(self.background_blend.transform),
# Lambda(self.gaussian_filter.transform), # Gaussian
Lambda(self.time_mask.transform),
Lambda(self.freq_mask.transform),
# iaa.CenterCropToFixedSize(height=90, width=None),
]
)
def build_test(self):
return Compose([
# iaa.CenterCropToFixedSize(height=90, width=None).augment_image,
# iaa.Lambda(func_images=self.gaussian_filter.func_images).augment_image, # Gaussian
# Lambda(self.background_supp.transform), # Background suppresion
Lambda(minmax_norm),
# CenterCrop(100, 32),
Resize(
self.image_size[0],
self.image_size[1],
interpolation=cv2.INTER_CUBIC,
),
Lambda(normalize),
ToTensor(),
])
def build_train(self):
return Compose([
self.aug,
# RandomCrop(100, 32),
Resize(
self.image_size[0],
self.image_size[1],
interpolation=cv2.INTER_CUBIC,
),
Lambda(normalize),
# T.RandomErasing(),
ToTensor(),
])
new_image = canvas + image
#limiting brightness to 255
new_image = np.vectorize(lambda x: x if x < 255 else 255)(new_image)
return new_image
augmentations = Compose([
ShiftScaleRotate(shift_limit=0.07,
scale_limit=0.07,
rotate_limit=50,
border_mode=cv2.BORDER_CONSTANT,
value=0,
p=0.95),
Lambda(image=randomBlotch, p=0.7),
ToFloat(max_value=255) # normalizes the data to [0,1] in float
])
class AugmentedDataSequence(Sequence):
def __init__(self, x_set, y_set, batch_size=32):
self.x = x_set
self.y = y_set
self.batch_size = batch_size
def __len__(self):
return int(np.ceil((len(self.x) + 0.0) / self.batch_size))
def __getitem__(self, index):
x_batch = self.x[index * self.batch_size:(index + 1) * self.batch_size]
std=[0.229, 0.224, 0.225],
),
#ToTensorV2(),
])
model = smp.Unet(encoder_name='se_resnext50_32x4d',
encoder_weights='imagenet',
activation='sigmoid')
model = torch.load(os.path.join(path.realpath(path.curdir)+MODEL_SAVE_DIR, 'model.pth'), map_location=torch.device(device))
model.to(device);
model.eval();
identity_trfm = Lambda(image = lambda x,cols=None,rows=None : x)
identity = rasterio.Affine(1, 0, 0, 0, 1, 0)
transforms = ValTransforms()
p = pathlib.Path(IMAGE_DIR)
subm = {}
for i, filename in enumerate(p.glob('*.tiff')):
dataset = rasterio.open(filename.as_posix(), transform=identity)
print(dataset.shape)
slices = make_grid(dataset.shape, window=WINDOW, min_overlap=MIN_OVERLAP)
preds = np.zeros(dataset.shape, dtype=np.uint8)
for (x1,x2,y1,y2) in slices:
