This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pytorch_toolbelt.modules import ABN, GlobalAvgPool2d | |
from pytorch_toolbelt.modules import decoders as D | |
from pytorch_toolbelt.modules import encoders as E | |
from torch import nn | |
from torch.nn import functional as F | |
class FPNCatSegmentationModel(nn.Module): | |
def __init__( | |
self, |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def test_loss_profiling(): | |
loss = nn.BCEWithLogitsLoss() | |
with torch.autograd.profiler.profile(use_cuda=True) as prof: | |
input = torch.randn((8, 1, 128, 128)).cuda() | |
input.requires_grad = True | |
target = torch.randint(1, (8, 1, 128, 128)).cuda().float() | |
for i in range(10): | |
l = loss(input, target) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class RAMDataset(Dataset): | |
def __init__(image_fnames, targets): | |
self.targets = targets | |
self.images = [] | |
for fname in tqdm(image_fnames, desc="Loading files in RAM"): | |
with open(fname, "rb") as f: | |
self.images.append(f.read()) | |
def __len__(self): | |
return len(self.targets) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class MySegmentationDataset(Dataset): | |
... | |
def __getitem__(self, index): | |
image = cv2.imread(self.images[index]) | |
target = cv2.imread(self.masks[index]) | |
# No data normalization and type casting here | |
return torch.from_numpy(image).permute(2,0,1).contiguous(), | |
torch.from_numpy(target).permute(2,0,1).contiguous() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Bad practice, don't return tuple | |
class RetinaNet(nn.Module): | |
... | |
def forward(self, image): | |
x = self.encoder(image) | |
x = self.decoder(x) | |
bboxes, scores = self.head(x) | |
return bboxes, scores |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class RetinaNet(nn.Module): | |
RETINA_NET_OUTPUT_BBOXES = "bboxes" | |
RETINA_NET_OUTPUT_SCORES = "scores" | |
... | |
def forward(self, image): | |
x = self.encoder(image) | |
x = self.decoder(x) | |
bboxes, scores = self.head(x) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://github.com/BloodAxe/Kaggle-2020-Alaska2/blob/master/alaska2/models/timm.py#L104 | |
def forward(self, **kwargs): | |
x = kwargs[self.input_key] | |
x = self.rgb_bn(x) | |
x = self.encoder.forward_features(x) | |
embedding = self.pool(x) | |
result = { | |
OUTPUT_PRED_MODIFICATION_FLAG: self.flag_classifier(self.drop(embedding)), | |
OUTPUT_PRED_MODIFICATION_TYPE: self.type_classifier(self.drop(embedding)), |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://github.com/BloodAxe/Kaggle-2020-Alaska2/blob/master/alaska2/dataset.py#L373 | |
class TrainingValidationDataset(Dataset): | |
def __init__( | |
self, | |
images: Union[List, np.ndarray], | |
targets: Optional[Union[List, np.ndarray]], | |
quality: Union[List, np.ndarray], | |
bits: Optional[Union[List, np.ndarray]], | |
transform: Union[A.Compose, A.BasicTransform], | |
features: List[str], |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://github.com/BloodAxe/Kaggle-2020-Alaska2 | |
callbacks += [ | |
CriterionCallback( | |
input_key=INPUT_TRUE_MODIFICATION_FLAG, | |
output_key=OUTPUT_PRED_MODIFICATION_FLAG, | |
criterion_key="bce" | |
), | |
CriterionCallback( | |
input_key=INPUT_TRUE_MODIFICATION_TYPE, |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import torch | |
def main(): | |
torch.autograd.detect_anomaly() | |
... | |
# Rest of the training code | |
# OR | |
class MyNumericallyUnstableLoss(nn.Module): |