def visualize_predictions(image_logger, max_samples, metric_fn, logits, gt):
num_samples = min(len(gt), max_samples)
metrics = to_numpy(
metric_fn(from_numpy(logits), from_numpy(gt), average=False))
order = np.argsort(metrics)
gt = gt[order][:num_samples]
logits = logits[order][:num_samples]
metrics = metrics[order][:num_samples]
probs = 1 / (1 + np.exp(-logits.squeeze()))
samples_per_row = 16
num_rows = int(np.ceil(num_samples / samples_per_row)) * 2
plt.figure(figsize=(6, 1 * num_rows))
for i in range(num_samples):
plt.subplot(num_rows, samples_per_row,
(i // samples_per_row) * samples_per_row + i + 1)
plt.title(f'{metrics[i]:.1f}')
plt.imshow(probs[i], vmin=0, vmax=1)
plt.xticks([])
plt.yticks([])
plt.subplot(num_rows, samples_per_row,
(i // samples_per_row + 1) * samples_per_row + i + 1)
plt.imshow(gt[i])
plt.xticks([])
plt.yticks([])
plt.gcf().tight_layout()
plt.subplots_adjust(hspace=0.1, wspace=0.1)
image_logger(plt.gcf())
def predict(checkpoint_path, batch_size=1, limit=None):
model = load_checkpoint(checkpoint_path)
model = as_cuda(model)
torch.set_grad_enabled(False)
model.eval()
records = []
ids = list(
map(lambda path: path.split('/')[-1],
get_images_in('data/test')))[:limit]
test_generator = get_test_generator(batch_size, limit)
for inputs, _ in tqdm(test_generator, total=len(test_generator)):
inputs = from_numpy(inputs)
outputs = model(inputs)
masks = to_numpy(torch.argmax(outputs, dim=1))
for mask in masks:
_id = ids.pop(0)
instance_masks = extract_instance_masks_from_binary_mask(mask)
if len(instance_masks) == 0:
records.append((_id, None))
else:
for instance_mask in instance_masks:
records.append((_id, encode_rle(instance_mask)))
image_ids, encoded_pixels = zip(*records)
df = pd.DataFrame({'ImageId': image_ids, 'EncodedPixels': encoded_pixels})
df.to_csv('./data/submissions/__latest.csv', index=False)
def predict(checkpoint_path, batch_size=1, limit=None, tta=False):
model = load_checkpoint(checkpoint_path)
model = as_cuda(model)
torch.set_grad_enabled(False)
model.eval()
records = []
ids = list(
map(lambda path: path.split('/')[-1],
get_images_in('data/test')))[:limit]
test_generator = get_test_generator(batch_size, limit)
for batch in tqdm(test_generator, total=len(test_generator)):
batch = from_numpy(batch)
masks = None
if tta:
accumulated_outputs = 0
for i, should_flip in product(range(4), [False, True]):
image_batch = batch['image']
image_batch = rotate_image_batch(image_batch, i)
if should_flip: image_batch = flip_image_batch(image_batch)
outputs = torch.sigmoid(model({'image': image_batch})['mask'])
if should_flip: outputs = flip_image_batch(outputs)
outputs = rotate_image_batch(outputs, -i)
accumulated_outputs += outputs
accumulated_outputs /= 8
masks = to_numpy(accumulated_outputs[:, 0, :, :])
else:
outputs = model(batch)
outputs['mask'] = torch.sigmoid(outputs['mask'])
masks = to_numpy(outputs['mask'][:, 0, :, :])
for mask in masks:
_id = ids.pop(0)
instance_masks = extract_instance_masks_from_soft_mask(mask)
if len(instance_masks) == 0:
records.append((_id, None))
else:
for instance_mask in instance_masks:
records.append((_id, encode_rle(instance_mask)))
image_ids, encoded_pixels = zip(*records)
df = pd.DataFrame({'ImageId': image_ids, 'EncodedPixels': encoded_pixels})
df.to_csv('./data/submissions/__latest.csv', index=False)
def predict(checkpoint_path,
submission_path,
batch_size=1,
limit=None,
tta=False):
model = load_checkpoint(checkpoint_path)
model = as_cuda(model)
torch.set_grad_enabled(False)
model.eval()
records = []
ids = list(
map(lambda path: path.split('/')[-1],
get_images_in('data/test')))[:limit]
submission = pd.read_csv(submission_path)
print('Num masks before', len(submission))
test_generator = get_test_generator(batch_size, limit, classification=True)
for batch in tqdm(test_generator, total=len(test_generator)):
batch = from_numpy(batch)
outputs = model(batch)
if tta:
batch['image'] = batch['image'].flip(dims=(3, ))
flipped_outputs = model(batch)
outputs['has_ships'] = (
torch.sigmoid(outputs['has_ships']) +
torch.sigmoid(flipped_outputs['has_ships'])) / 2
else:
outputs['has_ships'] = torch.sigmoid(outputs['has_ships'])
pred_labels = to_numpy(outputs['has_ships'][:, 0].round().long())
for pred in pred_labels:
_id = ids.pop(0)
if pred == 1: continue
submission = submission[submission['ImageId'] != _id].copy()
submission = submission.append(
{
'ImageId': _id,
'EncodedPixels': None
}, ignore_index=True)
print('Num masks after', len(submission))
submission.to_csv('./data/submissions/__latest_filtered.csv', index=False)
def fit_model(model,
train_generator,
validation_generator,
optimizer,
loss_fn,
num_epochs,
logger,
callbacks=[],
metrics=[]):
for epoch in tqdm(range(num_epochs)):
num_batches = len(train_generator)
logs = {}
logs['train_loss'] = 0
for func in metrics:
logs[f'train_{func.__name__}'] = 0
model.train()
torch.set_grad_enabled(True)
for callback in callbacks:
callback.on_train_begin()
for inputs, gt in tqdm(train_generator, total=num_batches):
inputs, gt = from_numpy(inputs), from_numpy(gt)
optimizer.zero_grad()
outputs = model(inputs)
loss = loss_fn(outputs, gt)
loss.backward()
optimizer.step()
logs['train_loss'] += loss.data[0]
for func in metrics:
logs[f'train_{func.__name__}'] += func(outputs.detach(), gt)
for callback in callbacks:
callback.on_train_batch_end(loss.data[0])
logs['train_loss'] /= num_batches
for func in metrics:
logs[f'train_{func.__name__}'] /= num_batches
logs['val_loss'] = 0
for func in metrics:
logs[f'val_{func.__name__}'] = 0
all_outputs = []
all_gt = []
num_batches = len(validation_generator)
model.eval()
torch.set_grad_enabled(False)
for inputs, gt in tqdm(validation_generator, total=num_batches):
all_gt.append(gt)
inputs, gt = from_numpy(inputs), from_numpy(gt)
outputs = model(inputs)
# TODO AS: Extract as cmd opt
flipped_outputs = torch.sigmoid(
model(inputs.flip(dims=(3, ))).flip(dims=(3, )))
outputs = torch.sigmoid(outputs)
outputs = (outputs + flipped_outputs) / 2
outputs = torch.log(outputs / (1 - outputs))
logs['val_loss'] += loss_fn(outputs, gt).data[0]
for func in metrics:
logs[f'val_{func.__name__}'] += func(outputs.detach(), gt)
if isinstance(outputs, tuple):
all_outputs.append(list(map(to_numpy, outputs)))
else:
all_outputs.append(to_numpy(outputs))
logs['val_loss'] /= num_batches
for func in metrics:
logs[f'val_{func.__name__}'] /= num_batches
if isinstance(all_outputs[0], tuple):
all_outputs = list(map(np.concatenate, zip(*all_outputs)))
else:
all_outputs = np.concatenate(all_outputs)
all_gt = np.concatenate(all_gt)
for callback in callbacks:
callback.on_validation_end(logs, all_outputs, all_gt)
epoch_rows = [['epoch', epoch]]
for name, value in logs.items():
epoch_rows.append([name, f'{value:.3f}'])
logger(tabulate(epoch_rows))
def fit_model(
model,
train_generator,
validation_generator,
optimizer,
loss_fn,
num_epochs,
logger,
callbacks=[],
metrics=[],
steps_per_epoch=None
):
if steps_per_epoch is None:
steps_per_epoch = len(train_generator)
train_generator = looped(train_generator)
for epoch in tqdm(range(num_epochs)):
num_batches = steps_per_epoch
logs = {}
logs['train_loss'] = 0
for func in metrics: logs[f'train_{func.__name__}'] = 0
model.train()
torch.set_grad_enabled(True)
for callback in callbacks: callback.on_train_begin(logs)
for i in tqdm(range(num_batches)):
batch = from_numpy(next(train_generator))
optimizer.zero_grad()
outputs = model(batch)
loss = loss_fn(outputs, batch)
loss.backward()
optimizer.step()
logs['train_loss'] += loss.data[0]
logs['batch_loss'] = loss.data[0]
for func in metrics: logs[f'train_{func.__name__}'] += func(outputs, batch)
for callback in callbacks: callback.on_train_batch_end(logs, outputs, batch)
logs.pop('batch_loss')
logs['train_loss'] /= num_batches
for func in metrics: logs[f'train_{func.__name__}'] /= num_batches
logs['val_loss'] = 0
for func in metrics: logs[f'val_{func.__name__}'] = 0
num_batches = len(validation_generator)
model.eval()
torch.set_grad_enabled(False)
for batch in tqdm(validation_generator, total=num_batches):
batch = from_numpy(batch)
outputs = model(batch)
logs['val_loss'] += loss_fn(outputs, batch).data[0]
for func in metrics: logs[f'val_{func.__name__}'] += func(outputs, batch)
for callback in callbacks: callback.on_validation_batch_end(logs, outputs, batch)
logs['val_loss'] /= num_batches
for func in metrics: logs[f'val_{func.__name__}'] /= num_batches
for callback in callbacks: callback.on_validation_end(logs)
epoch_rows = [['epoch', epoch]]
for name, value in logs.items():
epoch_rows.append([name, f'{value:.3f}'])
logger(tabulate(epoch_rows))
def on_validation_end(self, logs, outputs, gt):
values = to_numpy(
self.metric_fn(from_numpy(outputs), from_numpy(gt), average=False))
plt.hist(values, bins=20)
plt.title(self.metric_fn.__name__)
self.image_logger(plt.gcf())