def main():
with timer('load data'):
df = pd.read_csv(TEST_PATH)
df[['ID', 'Image', 'Diagnosis']] = df['ID'].str.split('_', expand=True)
df = df[['Image', 'Diagnosis', 'Label']]
df.drop_duplicates(inplace=True)
df = df.pivot(index='Image', columns='Diagnosis',
values='Label').reset_index()
df['Image'] = 'ID_' + df['Image']
df = df[["Image"]]
ids = df["Image"].values
gc.collect()
with timer('preprocessing'):
test_augmentation = Compose([
CenterCrop(512 - 50, 512 - 50, p=1.0),
Resize(img_size, img_size, p=1)
])
test_dataset = RSNADatasetTest(df,
img_size,
IMAGE_PATH,
id_colname=ID_COLUMNS,
transforms=test_augmentation,
black_crop=False,
subdural_window=True,
conc_type="concat_all",
conc_type2="concat_prepost",
n_tta=N_TTA)
test_loader = DataLoader(test_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=16,
pin_memory=True)
del df, test_dataset
gc.collect()
with timer('create model'):
model = CnnModel(num_classes=N_CLASSES,
encoder="se_resnext50_32x4d",
pretrained="imagenet",
pool_type="avg")
model.load_state_dict(torch.load(model_path))
model.to(device)
model = torch.nn.DataParallel(model)
with timer('predict'):
pred = predict(model, test_loader, device, n_tta=N_TTA)
pred = np.clip(pred, 1e-6, 1 - 1e-6)
with timer('sub'):
sub = pd.DataFrame(pred, columns=TARGET_COLUMNS)
sub["ID"] = ids
sub = sub.set_index("ID")
sub = sub.unstack().reset_index()
sub["ID"] = sub["ID"] + "_" + sub["level_0"]
sub = sub.rename(columns={0: "Label"})
sub = sub.drop("level_0", axis=1)
LOGGER.info(sub.head())
sub.to_csv("../output/{}_sub_st2.csv".format(EXP_ID), index=False)
def main():
with timer('load data'):
df = pd.read_csv(TRAIN_PATH)[:10]
df = df[df.Image != "ID_6431af929"].reset_index(drop=True)
df.loc[df.pre_SOPInstanceUID == "ID_6431af929",
"pre1_SOPInstanceUID"] = df.loc[df.pre_SOPInstanceUID ==
"ID_6431af929", "Image"]
df.loc[df.post_SOPInstanceUID == "ID_6431af929",
"post1_SOPInstanceUID"] = df.loc[df.post_SOPInstanceUID ==
"ID_6431af929", "Image"]
df = df[["Image", "pre1_SOPInstanceUID", "post1_SOPInstanceUID"]]
ids = df["Image"].values
gc.collect()
with timer('preprocessing'):
test_augmentation = Compose([
CenterCrop(512 - 50, 512 - 50, p=1.0),
Resize(img_size, img_size, p=1)
])
test_dataset = RSNADatasetTest(df,
img_size,
IMAGE_PATH,
id_colname=ID_COLUMNS,
transforms=test_augmentation,
black_crop=False,
three_window=True,
rescaling=False,
n_tta=N_TTA)
test_loader = DataLoader(test_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=16,
pin_memory=True)
del df, test_dataset
gc.collect()
with timer('create model'):
model = CnnModel(num_classes=N_CLASSES,
encoder="se_resnext50_32x4d",
pretrained="imagenet",
pool_type="avg")
model.load_state_dict(torch.load(model_path))
model.to(device)
model = torch.nn.DataParallel(model)
with timer('predict'):
pred = predict(model, test_loader, device, n_tta=N_TTA)
pred = np.clip(pred, 1e-6, 1 - 1e-6)
with timer('sub'):
sub = pd.DataFrame(pred, columns=TARGET_COLUMNS)
sub["ID"] = ids
sub = sub.set_index("ID")
sub = sub.unstack().reset_index()
sub["ID"] = sub["ID"] + "_" + sub["level_0"]
sub = sub.rename(columns={0: "Label"})
sub = sub.drop("level_0", axis=1)
LOGGER.info(sub.head())
sub.to_csv("../output/{}_train.csv".format(EXP_ID), index=False)
def predict_loss(prev, paths, split_df):
# prev: true value
# paths: paths to the model weights
t_preds = []
for tm in range(3):
tf.reset_default_graph()
t_preds.append(
predict(paths[-1:],
build_hparams(hparams.params_s32),
back_offset=0,
predict_window=288,
n_models=3,
target_model=tm,
seed=2,
batch_size=50,
asgd=True,
split_df=split_df))
preds = sum(t_preds) / 3
preds.index = [idx.decode('ascii') for idx in preds.index]
# mean mae
res = 0
for idx in preds.index:
res += np.abs(preds.loc[idx, :] - prev.loc[idx, -288:]).sum()
res /= len(preds.index) * 288
return preds, res
def predict_loss(paths):
# paths: paths to the model weights
t_preds = []
for tm in range(3):
tf.reset_default_graph()
t_preds.append(predict(paths[-1:], build_hparams(hparams.params_s32),
n_models=3, target_model=tm, seed=5, batch_size=50, asgd=True))
preds=sum(t_preds) /3
return preds
def main():
with timer('load data'):
df = pd.read_csv(TEST_PATH)
df["post_SOPInstanceUID"] = df["post_SOPInstanceUID"].fillna(
df["SOPInstanceUID"])
df["pre_SOPInstanceUID"] = df["pre_SOPInstanceUID"].fillna(
df["SOPInstanceUID"])
df = df[["Image", "pre_SOPInstanceUID", "post_SOPInstanceUID"]]
ids = df["Image"].values
pre_ids = df["pre_SOPInstanceUID"].values
pos_ids = df["post_SOPInstanceUID"].values
gc.collect()
with timer('preprocessing'):
test_augmentation = Compose([
CenterCrop(512 - 50, 512 - 50, p=1.0),
Resize(img_size, img_size, p=1)
])
test_dataset = RSNADatasetTest(df,
img_size,
IMAGE_PATH,
id_colname=ID_COLUMNS,
transforms=test_augmentation,
black_crop=False,
subdural_window=True,
n_tta=N_TTA)
test_loader = DataLoader(test_dataset,
batch_size=batch_size,
shuffle=False,
num_workers=16,
pin_memory=True)
del df, test_dataset
gc.collect()
with timer('create model'):
model = CnnModel(num_classes=N_CLASSES,
encoder="se_resnext50_32x4d",
pretrained="imagenet",
pool_type="avg")
model.load_state_dict(torch.load(model_path))
model.to(device)
model = torch.nn.DataParallel(model)
with timer('predict'):
pred = predict(model, test_loader, device, n_tta=N_TTA)
pred = np.clip(pred, 1e-6, 1 - 1e-6)
with timer('sub'):
sub = pd.DataFrame(pred, columns=TARGET_COLUMNS)
sub["ID"] = ids
sub["PRE_ID"] = pre_ids
sub["POST_ID"] = pos_ids
sub = postprocess_multitarget(sub)
LOGGER.info(sub.head())
sub.to_csv("../output/{}_sub_st2.csv".format(EXP_ID), index=False)
def predict(self, text_x):
if not hasattr(self, 'dataset'):
raise ValueError(
'Cannnot call predict or evaluate in untrained model. Train First!'
)
self.dataset.clear_test_set()
for _x in text_x:
self.dataset.add_data_entry(_x.tolist(), 0, part='test')
return predict(
model=self.model,
iterator_function=self.dataset.get_next_test_batch,
_batch_count=self.dataset.initialize_test_batches(),
cuda_device=0 if self.cuda else -1,
)
def index():
learning_gif_url = get_gif_url("learning")
# Get search query
if request.method == "POST":
user_input = request.form.get("user_input")
# If no query, user_input is 'You're awesome!'
else:
user_input = "You're awesome!"
print("user_input = ", user_input)
# Predict and get sentiment text
sentiment = predict(user_input, cv, log_model)
return render_template("index.html",
user_input=user_input,
sentiment=sentiment,
learning_gif_url=learning_gif_url)
def predict_loss(prev, paths):
# prev: true value
# paths: paths to the model weights
t_preds = []
for tm in range(3):
tf.reset_default_graph()
t_preds.append(
predict(paths[-1:],
build_hparams(hparams.params_s32),
n_models=3,
target_model=tm,
seed=5,
batch_size=50,
asgd=True))
preds = sum(t_preds) / 3
# mean mae
res = 0
for idx in preds.index:
res += np.abs(preds[idx] - prev[idx]) / prev[idx]
res /= 72
return preds, res
def main():
with timer('load data'):
df = pd.read_csv(TRAIN_PATH)
df["loc_x"] = df["loc_x"] / 100
df["loc_y"] = df["loc_y"] / 100
y = df[TARGET_COLUMNS].values
df = df[[ID_COLUMNS]]
gc.collect()
with timer("split data"):
folds = StratifiedKFold(n_splits=5, shuffle=True, random_state=0).split(df, y)
for n_fold, (train_index, val_index) in enumerate(folds):
train_df = df.loc[train_index]
val_df = df.loc[val_index]
y_train = y[train_index]
y_val = y[val_index]
if n_fold == fold_id:
break
with timer('preprocessing'):
train_augmentation = Compose([
HorizontalFlip(p=0.5),
OneOf([
ElasticTransform(p=0.5, alpha=120, sigma=120 * 0.05, alpha_affine=120 * 0.03),
GridDistortion(p=0.5),
OpticalDistortion(p=1, distort_limit=2, shift_limit=0.5)
], p=0.5),
RandomBrightnessContrast(p=0.5),
ShiftScaleRotate(rotate_limit=20, p=0.5),
Resize(img_size, img_size, p=1)
])
val_augmentation = Compose([
Resize(img_size, img_size, p=1)
])
train_dataset = KDDataset(train_df, y_train, img_size, IMAGE_PATH, id_colname=ID_COLUMNS,
transforms=train_augmentation)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=2, pin_memory=True)
val_dataset = KDDataset(val_df, y_val, img_size, IMAGE_PATH, id_colname=ID_COLUMNS,
transforms=val_augmentation)
val_loader = DataLoader(val_dataset, batch_size=batch_size, shuffle=False, num_workers=2, pin_memory=True)
del df, train_dataset, val_dataset
gc.collect()
with timer('create model'):
model = CnnModel(num_classes=N_CLASSES, encoder="se_resnext50_32x4d",
pretrained="../input/pytorch-pretrained-models/se_resnext50_32x4d-a260b3a4.pth",
pool_type="avg")
if model_path is not None:
model.load_state_dict(torch.load(model_path))
model.to(device)
criterion = torch.nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4, eps=1e-4)
# model, optimizer = amp.initialize(model, optimizer, opt_level="O1", verbosity=0)
with timer('train'):
best_score = 0
for epoch in range(1, epochs + 1):
seed_torch(SEED + epoch)
if epoch == epochs - 3:
for param_group in optimizer.param_groups:
param_group['lr'] = param_group['lr'] * 0.1
LOGGER.info("Starting {} epoch...".format(epoch))
tr_loss = train_one_epoch(model, train_loader, criterion, optimizer, device, N_CLASSES)
LOGGER.info('Mean train loss: {}'.format(round(tr_loss, 5)))
y_pred, target, val_loss = validate(model, val_loader, criterion, device, N_CLASSES)
score = roc_auc_score(target, y_pred)
LOGGER.info('Mean val loss: {}'.format(round(val_loss, 5)))
LOGGER.info('val score: {}'.format(round(score, 5)))
if score > best_score:
best_score = score
np.save("y_pred.npy", y_pred)
torch.save(model.state_dict(), save_path)
np.save("target.npy", target)
with timer('predict'):
test_df = pd.read_csv(TEST_PATH)
test_ids = test_df["id"].values
test_augmentation = Compose([
Resize(img_size, img_size, p=1)
])
test_dataset = KDDatasetTest(test_df, img_size, TEST_IMAGE_PATH, id_colname=ID_COLUMNS,
transforms=test_augmentation, n_tta=2)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False, num_workers=2, pin_memory=True)
model.load_state_dict(torch.load(save_path))
pred = predict(model, test_loader, device, N_CLASSES, n_tta=2)
print(pred.shape)
results = pd.DataFrame({"id": test_ids,
"is_star": pred.reshape(-1)})
results.to_csv("results.csv", index=False)
def main(seed):
with timer('load data'):
df = pd.read_csv(FOLD_PATH)
with timer('preprocessing'):
val_df = df[df.fold_id == FOLD_ID]
val_augmentation = None
val_dataset = SeverDataset(val_df,
IMG_DIR,
IMG_SIZE,
N_CLASSES,
id_colname=ID_COLUMNS,
transforms=val_augmentation)
val_loader = DataLoader(val_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=8)
del val_df, df, val_dataset
gc.collect()
with timer('create model'):
model = smp.Unet('resnet34',
encoder_weights="imagenet",
classes=N_CLASSES,
encoder_se_module=True,
decoder_semodule=True,
h_columns=False,
skip=True,
act="swish",
freeze_bn=True,
classification=CLASSIFICATION,
attention_type="cbam")
model.load_state_dict(torch.load(base_model))
model.to(device)
criterion = torch.nn.BCEWithLogitsLoss()
with timer('predict'):
valid_loss, y_pred, y_true, cls = predict(
model,
val_loader,
criterion,
device,
classification=CLASSIFICATION)
LOGGER.info('Mean valid loss: {}'.format(round(valid_loss, 5)))
scores = []
for i, (th, remove_mask_pixel) in enumerate(zip(ths, remove_pixels)):
sum_val_preds = np.sum(
y_pred[:, i, :, :].reshape(len(y_pred), -1) > th, axis=1)
cls_ = cls[:, i]
best = 0
for th_cls in np.linspace(0, 1, 101):
val_preds_ = copy.deepcopy(y_pred[:, i, :, :])
val_preds_[sum_val_preds < remove_mask_pixel] = 0
val_preds_[cls_ <= th_cls] = 0
scores = []
for y_val_, y_pred_ in zip(y_true[:, i, :, :], val_preds_):
score = dice(y_val_, y_pred_ > 0.5)
if np.isnan(score):
scores.append(1)
else:
scores.append(score)
if np.mean(scores) >= best:
best = np.mean(scores)
best_th = th_cls
else:
break
LOGGER.info('dice={} on {}'.format(best, best_th))
scores.append(best)
LOGGER.info('holdout dice={}'.format(np.mean(scores)))
def main(seed):
with timer('load data'):
df = pd.read_csv(FOLD_PATH)
if N_CLASSES == 3:
df.drop("EncodedPixels_2", axis=1, inplace=True)
df = df.rename(columns={"EncodedPixels_3": "EncodedPixels_2"})
df = df.rename(columns={"EncodedPixels_4": "EncodedPixels_3"})
with timer('preprocessing'):
val_df = df[df.fold_id == FOLD_ID]
val_augmentation = None
val_dataset = SeverDataset(val_df, IMG_DIR, IMG_SIZE, N_CLASSES, id_colname=ID_COLUMNS,
transforms=val_augmentation)
val_loader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=8)
del val_df, df, val_dataset
gc.collect()
with timer('create model'):
model = smp_old.Unet('resnet34', encoder_weights="imagenet", classes=N_CLASSES, encoder_se_module=True,
decoder_semodule=True, h_columns=False, skip=True, act="swish", freeze_bn=True,
classification=CLASSIFICATION)
model.load_state_dict(torch.load(base_model))
model.to(device)
model.eval()
criterion = torch.nn.BCEWithLogitsLoss()
with timer('predict'):
valid_loss, y_pred, y_true, cls = predict(model, val_loader, criterion, device, classification=CLASSIFICATION)
LOGGER.info('Mean valid loss: {}'.format(round(valid_loss, 5)))
scores = []
all_scores = []
min_sizes = [300, 0, 600, 1600]
for i in range(N_CLASSES):
if i == 1:
continue
best = 0
count = 0
min_size = min_sizes[i]
for th in [0.7+i*0.01 for i in range(30)]:
val_preds_ = copy.deepcopy(y_pred[:, i, :, :])
scores_ = []
all_scores_ = []
for y_val_, y_pred_ in zip(y_true[:, i, :, :], val_preds_):
y_pred_ = post_process(y_pred_ > 0.5, y_pred_, min_size, th)
score = dice(y_val_, y_pred_)
if np.isnan(score):
scores_.append(1)
else:
scores_.append(score)
LOGGER.info('dice={} on {}'.format(np.mean(scores_), th))
if np.mean(scores_) >= best:
best = np.mean(scores_)
count = 0
else:
count += 1
if count == 3:
break
scores.append(best)
all_scores.append(all_scores_)
LOGGER.info('holdout dice={}'.format(np.mean(scores)))
def main(seed):
with timer('load data'):
df = pd.read_csv(FOLD_PATH)
y1 = (df.EncodedPixels_1 != "-1").astype("float32").values.reshape(-1, 1)
y2 = (df.EncodedPixels_2 != "-1").astype("float32").values.reshape(-1, 1)
y3 = (df.EncodedPixels_3 != "-1").astype("float32").values.reshape(-1, 1)
y4 = (df.EncodedPixels_4 != "-1").astype("float32").values.reshape(-1, 1)
y = np.concatenate([y1, y2, y3, y4], axis=1)
with timer('preprocessing'):
val_df = df[df.fold_id == FOLD_ID]
y_val = y[df.fold_id == FOLD_ID]
val_dataset = SeverCLSDataset(val_df, IMG_DIR, IMG_SIZE, N_CLASSES, y_val, id_colname=ID_COLUMNS,
transforms=None)
val_loader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=8, pin_memory=True)
models = []
model = cls_models.SEResNext(num_classes=N_CLASSES)
model.load_state_dict(torch.load(base_model_cls))
model.to(device)
model.eval()
models.append(model)
"""model = cls_models.ResNet(num_classes=N_CLASSES, pretrained=None)
model.load_state_dict(torch.load(base_model_res))
model.to(device)
model.eval()
models.append(model)"""
with timer('predict cls'):
criterion = torch.nn.BCEWithLogitsLoss()
valid_loss, y_val, y_true = predict_cls(models, val_loader, criterion, device)
#y_val = np.load("../exp_cls/y_pred_ema_ckpt8.npy")
LOGGER.info("val loss={}".format(valid_loss))
with timer('preprocessing seg'):
val_augmentation = None
val_dataset = SeverDataset(val_df, IMG_DIR, IMG_SIZE, N_CLASSES, id_colname=ID_COLUMNS,
transforms=val_augmentation, class_y=y_val)
val_loader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, num_workers=8)
del val_df, df, val_dataset
gc.collect()
with timer('create model'):
model = smp.Unet('resnet34', encoder_weights="imagenet", classes=N_CLASSES, encoder_se_module=True,
decoder_semodule=True, h_columns=False, skip=True, act="swish", freeze_bn=True,
classification=CLASSIFICATION, attention_type="cbam", center=True)
model.load_state_dict(torch.load(base_model))
model.to(device)
criterion = torch.nn.BCEWithLogitsLoss()
with timer('predict'):
valid_loss, y_pred, y_true, cls = predict(model, val_loader, criterion, device, classification=CLASSIFICATION)
LOGGER.info('Mean valid loss: {}'.format(round(valid_loss, 5)))
scores = []
for i, (th, remove_mask_pixel) in enumerate(zip(ths, remove_pixels)):
if i <= 1:
continue
sum_val_preds = np.sum(y_pred[:, i, :, :].reshape(len(y_pred), -1) > th, axis=1)
cls_ = cls[:, i]
best = 0
for th_cls in np.linspace(0, 1, 101):
val_preds_ = copy.deepcopy(y_pred[:, i, :, :])
val_preds_[sum_val_preds < remove_mask_pixel] = 0
val_preds_[cls_ <= th_cls] = 0
scores = []
for y_val_, y_pred_ in zip(y_true[:, i, :, :], val_preds_):
score = dice(y_val_, y_pred_ > 0.5)
if np.isnan(score):
scores.append(1)
else:
scores.append(score)
if np.mean(scores) >= best:
best = np.mean(scores)
best_th = th_cls
#else:
# break
LOGGER.info('dice={} on {}'.format(best, best_th))
scores.append(best)
LOGGER.info('holdout dice={}'.format(np.mean(scores)))
# embed_size=len(dct),
# device=device)
# model = Bi_RNN_ATTN(class_num=len(CATEGIRY_LIST),
# embed_size=len(dct),
# embed_dim=64,
# device=device)
lr = 0.001
optimizer = optim.Adam(model.parameters(), lr=lr)
# train
logger.info('training...')
history = trainer.train(model,
optimizer,
train_dl,
valid_dl,
device=device,
epochs=5)
# evaluate
loss, acc = trainer.evaluate(model, valid_dl, device=device)
# predict
logger.info('predicting...')
y_pred = trainer.predict(model, test_dl, device=device)
y_true = test_ds.labels
test_acc = (y_true == y_pred).sum() / y_pred.shape[0]
logger.info('test - acc: {}'.format(test_acc))
raw_smape = smape(true, pred)
masked_smape = np.ma.array(raw_smape, mask=np.isnan(raw_smape))
return masked_smape.mean()
from make_features import read_all
df_all = read_all()
df_all.columns
prev = df_all
paths = [p for p in tf.train.get_checkpoint_state('data/cpt/s32').all_model_checkpoint_paths]
t_preds = []
for tm in range(3):
tf.reset_default_graph()
t_preds.append(predict(paths, build_hparams(hparams.params_s32), back_offset=0, predict_window=63,
n_models=3, target_model=tm, seed=2, batch_size=2048, asgd=True))
preds=sum(t_preds) /3
missing_pages = prev.index.difference(preds.index)
# Use zeros for missing pages
rmdf = pd.DataFrame(index=missing_pages,
data=np.tile(0, (len(preds.columns),len(missing_pages))).T, columns=preds.columns)
f_preds = preds.append(rmdf).sort_index()
# Use zero for negative predictions
f_preds[f_preds < 0.5] = 0
# Rouns predictions to nearest int
f_preds = np.round(f_preds).astype(np.int64)
import argparse
from trainer import train, evaluate, predict
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Process some integers.')
parser.add_argument('mode', help='train, eval or predict')
args = parser.parse_args()
if args.mode == "train":
train()
if args.mode == "eval":
evaluate()
if args.mode == "predict":
predict()
def main(seed):
with timer('load data'):
df = pd.read_csv(FOLD_PATH)
with timer('preprocessing'):
val_df = df[df.fold_id == FOLD_ID]
val_augmentation = None
val_dataset = SeverDataset(val_df,
IMG_DIR,
IMG_SIZE,
N_CLASSES,
id_colname=ID_COLUMNS,
transforms=val_augmentation)
val_loader = DataLoader(val_dataset,
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=8)
del val_df, df, val_dataset
gc.collect()
with timer('create model'):
models = []
for p in base_model_res:
model = smp.Unet('resnet34',
encoder_weights="imagenet",
classes=N_CLASSES,
encoder_se_module=True,
decoder_semodule=True,
h_columns=False,
skip=True,
act="swish",
freeze_bn=True,
classification=CLASSIFICATION,
attention_type="cbam",
center=True)
model.load_state_dict(torch.load(p))
model.to(device)
model.eval()
models.append(model)
model = smp_old.Unet('resnet34',
encoder_weights="imagenet",
classes=N_CLASSES,
encoder_se_module=True,
decoder_semodule=True,
h_columns=False,
skip=True,
act="swish",
freeze_bn=True,
classification=CLASSIFICATION)
model.load_state_dict(torch.load(base_model_res_old))
model.to(device)
model.eval()
models.append(model)
criterion = torch.nn.BCEWithLogitsLoss()
with timer('predict'):
valid_loss, y_pred, y_true, cls = predict(
models,
val_loader,
criterion,
device,
classification=CLASSIFICATION)
LOGGER.info('Mean valid loss: {}'.format(round(valid_loss, 5)))
scores = []
all_scores = []
for i, th in enumerate(ths):
sum_val_preds = np.sum(
y_pred[:, i, :, :].reshape(len(y_pred), -1) > th, axis=1)
best = 0
for n_th, remove_mask_pixel in enumerate(
[200, 400, 600, 800, 1000, 1200, 1400, 1600, 1800]):
val_preds_ = copy.deepcopy(y_pred[:, i, :, :])
val_preds_[sum_val_preds < remove_mask_pixel] = 0
scores_ = []
all_scores_ = []
for y_val_, y_pred_ in zip(y_true[:, i, :, :], val_preds_):
score = dice(y_val_, y_pred_ > 0.5)
if np.isnan(score):
scores_.append(1)
else:
scores_.append(score)
LOGGER.info('dice={} on {}'.format(np.mean(scores_),
remove_mask_pixel))
if np.mean(scores_) >= best:
best = np.mean(scores_)
all_scores_.append(np.mean(scores_))
scores.append(np.mean(scores_))
all_scores.append(all_scores_)
LOGGER.info('holdout dice={}'.format(np.mean(scores)))
np.save("all_scores_fold{}.npy".format(FOLD_ID), np.array(all_scores))