def main_train(self, train_data, steps_per_epoch=None):
if steps_per_epoch is None:
steps_per_epoch = self.steps_per_epoch
from main_general import get_training_data
from preprocessing.image import get_flow
# TODO train
x_train, y_train, x_val, y_val = get_training_data(train_data)
# Generator
flow_tr = get_flow(x_train,
y_train,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in)
flow_va = get_flow(x_val,
y_val,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in)
epochs = 1
self.neural_net.train(
flow_tr,
validation=flow_va,
epochs=epochs,
steps_per_epoch=steps_per_epoch,
info=f'{set_net["name"]}_d{self.d}_k{self.k}_n{self.n_per_class}')
def set_img_x(self):
if self.set_nr == 13:
train_data = get_13(self.mod)
from data.datatools import imread
from data.conversion_tools import annotations2y
train_data.y_te = np.copy(train_data.y_tr)
train_data.y_tr = annotations2y(imread(
'/home/lameeus/data/ghent_altar/input/hierarchy/13_small/clean_annot_practical.png'
),
thresh=.9)
img_x, img_y, _, img_y_te = get_training_data(train_data)
# Normalise the input!
img_x = rescale0to1(img_x)
self.img_x = img_x
self.img_y_tr = img_y
self.img_y_te = img_y_te
train_data_10 = get_10lamb_6patches(self.mod).get_train_data_all()
img_x_10, img_y_10, _, _ = get_training_data(train_data_10)
# Normalise the input!
img_x_10 = rescale0to1(img_x_10)
self.flow_tr_set = get_flow(self.img_x,
self.img_y_tr,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ti)
self.flow_tr_10 = get_flow(img_x_10,
img_y_10,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ti)
n_multiply = 10
self.flow_tr_set_10 = get_flow([self.img_x] * n_multiply + [img_x_10],
[self.img_y_tr] * n_multiply +
[img_y_10],
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ti)
self.flow_ae_tr = get_flow(
self.img_x,
self.img_x,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ae,
)
def set_flow(train_data):
x_train, y_train, _, _ = get_training_data(train_data)
global flow_tr
flow_tr = get_flow(x_train,
y_train,
w_patch=w_patch,
w_ext_in=w_ext_in)
def get_flow_xy(xy):
if isinstance(xy, tuple):
x, y = map(batch2img, xy)
flow = get_flow(batch2img(x), batch2img(y))
return flow
elif isinstance(xy, (NumpyArrayIterator, )):
return xy
else:
raise TypeError(f'Unkown type for xy: {type(xy)}')
def set_flow(self):
# w_out should be 2+4*n
w_checker = 512
if self.ae_set_nr is not None:
img_x = []
for set_nr in self.ae_set_nr:
if set_nr == 10:
df = get_10lamb()
elif set_nr == 13:
df = get_13zach()
elif set_nr == 19:
df = get_19hand()
img_x_i = xy_from_df(df, mod)[0]
img_x.append()
else:
raise NotImplementedError()
img_x_lst = [self.img_x]
h_x, w_x = img_x.shape[:2]
x_ae_tr = []
x_ae_te = []
for i in range(int(np.ceil(h_x / w_checker))):
for j in range(int(np.ceil(w_x / w_checker))):
h0 = i * w_checker
w0 = j * w_checker
crop_x = img_x[h0:h0 + w_checker, w0:w0 + w_checker, ...]
if (i + j) % 2 == 0:
x_ae_tr.append(crop_x)
else:
x_ae_te.append(crop_x)
self.flow_ae_tr = get_flow(
x_ae_tr,
x_ae_tr,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ae,
)
self.flow_ae_te = get_flow(
x_ae_te,
x_ae_te,
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ae,
)
"""
Data for Segmentation of 10 lamb
"""
self.k_fold_train_data = get_10lamb_6patches(5)
self.flow_segm = get_flow(
self.img_x,
self.k_fold_train_data.get_train_data_all().get_y_train(),
w_patch=self.w_patch,
w_ext_in=self.w_ext_in_ti if self.ti else self.w_ext_in_ae,
)
def main():
"""
:return:
"""
### Settings
mod = 5
w_patch = 16 * 2
"""
Data (all important modalities)
"""
# folder_windows = r'C:\Users\Laurens_laptop_w\OneDrive - UGent\data\10lamb'
train_data = get_10lamb_old(mod)
img_x, img_y_tr, _, _ = get_training_data(train_data)
# Normalise the input!
img_x = rescale0to1(img_x)
"""
Train segmentation
1) reuse everything
2) fix encoder
"""
if 1:
if 1:
b_encoder_fixed = False
info_enc_fixed = '_enc_fixed' if b_encoder_fixed else ''
get_info = lambda: f'10lamb_kfold_pretrained{info_enc_fixed}/unet_enc_k{k}_ifold{i_fold}'
n_epochs = 40
k = 10
if k == 10:
epoch_w = 100
else:
raise NotImplementedError()
### Settings you don't have to change:
w_patch = 50
w_ext_in = 28
b_double = False
padding = 'valid'
# TODO flag for converting encoder to dilated conv
def get_unet_pretrained_encoder():
model_encoder = get_model_encoder()
encoder_inputs = model_encoder.input
decoder_outputs = decoder(model_encoder, f_out=2)
model_pretrained_unet = Model(encoder_inputs, decoder_outputs)
from methods.examples import compile_segm
compile_segm(model_pretrained_unet, lr=1e-4)
model_pretrained_unet.summary()
return model_pretrained_unet
"""
Train
"""
k_fold_train_data = get_10lamb_6patches(5)
for i_fold in range(6):
"""
Get a new network (not trained yet for segmentation)
"""
model_pretrained_unet = get_unet_pretrained_encoder()
n_pretrained_unet = NeuralNet(model_pretrained_unet)
"""
The data
"""
train_data_i = k_fold_train_data.k_split_i(i_fold)
info = get_info()
img_y_tr = train_data_i.get_y_train()
img_y_te = train_data_i.get_y_test()
flow_tr = get_flow(
img_x,
img_y_tr,
w_patch=w_patch, # Comes from 10
w_ext_in=w_ext_in)
flow_te = get_flow(
img_x,
img_y_te,
w_patch=w_patch, # Comes from 10
w_ext_in=w_ext_in)
n_pretrained_unet.train(flow_tr,
flow_te,
epochs=n_epochs,
verbose=1,
info=info)
"""
Prediction
"""
n_pretrained_unet.w_ext = w_ext_in
y_pred = n_pretrained_unet.predict(img_x)
concurrent([y_pred[..., 1]])
"""
Classification
"""
if 1:
im_clean = img_x[..., :3]
k = 8
i_fold = 3
epoch_last = 40
from methods.examples import kappa_loss, weighted_categorical_crossentropy
from performance.metrics import accuracy_with0, jaccard_with0
loss = weighted_categorical_crossentropy((1, 1))
list_y_pred = []
### K fold validation
k_fold_train_data = get_10lamb_6patches(5)
train_data_i = k_fold_train_data.k_split_i(i_fold)
img_y_tr = train_data_i.get_y_train()
img_y_te = train_data_i.get_y_test()
for epoch in np.arange(31, epoch_last + 1):
filepath_model = f'/scratch/lameeus/data/ghent_altar/net_weight/10lamb_kfold/ti_unet_k{k}_kfold{i_fold}/w_{epoch}.h5'
model = load_model(filepath_model,
custom_objects={
'loss': loss,
'accuracy_with0': accuracy_with0,
'jaccard_with0': jaccard_with0,
'kappa_loss': kappa_loss
})
n = NeuralNet(model, w_ext=10)
y_pred = n.predict(img_x)
list_y_pred.append(y_pred)
y_pred_mean = np.mean(list_y_pred, axis=0)
q1 = y_pred_mean[..., 1]
concurrent([q1, q1.round(), im_clean])
"""
Optimal threshold (making conf matrix symmetric, not based on maximising kappa)
"""
y_gt = np.any([img_y_tr, img_y_te], axis=0)
from performance.testing import _get_scores, filter_non_zero
def foo_performance(y_true, y_pred, thresh):
# is basically argmax
y_pred_thresh_arg = np.greater_equal(y_pred[..., 1], thresh)
y_true_flat, y_pred_thresh_arg_flat = filter_non_zero(
y_true, y_pred_thresh_arg)
y_te_argmax = np.argmax(y_true_flat, axis=-1)
# Kappa
return _get_scores(y_te_argmax, y_pred_thresh_arg_flat)[-1]
"""
1. BEST? PERFORMANCE based on test set
"""
print('1. Test distribution optimization')
thresh = optimal_test_thresh_equal_distribution(img_y_te, y_pred_mean)
q1_thresh = np.greater_equal(q1, thresh)
concurrent([q1, q1_thresh, im_clean])
print(f'thresh: {thresh}')
# Test, train, both
print('Kappa performance:')
print('\ttrain:', foo_performance(img_y_tr, y_pred_mean, thresh))
print('\ttestset:', foo_performance(img_y_te, y_pred_mean, thresh))
print('\tboth:', foo_performance(y_gt, y_pred_mean, thresh))
print('\nIncremental optimization on test set')
test_thresh2 = test_thresh_incremental(y_pred_mean,
img_y_tr,
img_y_te,
n=5,
verbose=0)
print('Kappa performance:')
print('\ttrain:', foo_performance(img_y_tr, y_pred_mean, test_thresh2))
print('\ttestset:', foo_performance(img_y_te, y_pred_mean,
test_thresh2))
print('\tboth:', foo_performance(y_gt, y_pred_mean, test_thresh2))
"""
2. based on train
"""
print('\n2. Training distribution optimization')
thresh = optimal_test_thresh_equal_distribution(img_y_tr, y_pred_mean)
q1_thresh = np.greater_equal(q1, thresh)
concurrent([q1, q1_thresh, im_clean])
print(f'thresh: {thresh}')
# Test, train, both
print('Kappa performance:')
print('\ttrain:', foo_performance(img_y_tr, y_pred_mean, thresh))
print('\ttestset:', foo_performance(img_y_te, y_pred_mean, thresh))
print('\tboth:', foo_performance(y_gt, y_pred_mean, thresh))
"""
3. CONSISTENT: based on train+set
"""
print('\n3. all GT distribution optimization')
thresh = optimal_test_thresh_equal_distribution(y_gt, y_pred_mean)
q1_thresh = np.greater_equal(q1, thresh)
concurrent([q1, q1_thresh, im_clean])
print(f'thresh: {thresh}')
# Test, train, both
print('Kappa performance:')
print('\ttrain:', foo_performance(img_y_tr, y_pred_mean, thresh))
print('\ttestset:', foo_performance(img_y_te, y_pred_mean, thresh))
print('\tboth:', foo_performance(y_gt, y_pred_mean, thresh))
if 0:
"""
4. DUMB/Not needed: Based on prediction of whole panel
"""
thresh = optimal_test_thresh_equal_distribution(y_gt,
y_pred_mean,
mask_true=False)
q1_thresh = np.greater_equal(q1, thresh)
concurrent([q1, q1_thresh, im_clean])
print('Done')
def train_segm(self):
folder_save = '/home/lameeus/data/ghent_altar/dataframes'
info_batchnorm = '_batchnorm' if self.batch_norm else ''
info_fixed = '_encfixed' if self.fixed_enc == 1 else '_prefixed' if self.fixed_enc == 2 else ''
info_model = 'tiunet' if self.ti else 'unet'
filename_single = f'pretrained/{info_model}_10lamb_kfold{info_fixed}{info_batchnorm}/d{self.depth}_single'
path_single = os.path.join(folder_save, filename_single + '.csv')
get_info = lambda: f'10lamb_kfold_pretrained{info_fixed}{info_batchnorm}/{info_model}_d{self.depth}_k{self.k}_ifold{i_fold}'
img_y_all = self.k_fold_train_data.get_train_data_all().get_y_train()
def get_model():
if self.ti:
model = self.get_tiunet_preenc(k=self.k, lr=self.lr_opt)
else:
model = self.get_unet_preenc(k=self.k, lr=self.lr_opt)
if self.fixed_enc == 2:
n_temp = NeuralNet(model)
folder_weights = '/scratch/lameeus/data/ghent_altar/net_weight'
folder1 = f'10lamb_kfold_pretrained{"_encfixed"}{info_batchnorm}'
folder2 = f'{info_model}_d{self.depth}_k{self.k}_ifold{i_fold}'
n_temp.load(os.path.join(folder_weights, folder1, folder2),
100)
del (n_temp)
return model
w_ext = self.w_ext_in_ti if self.ti else self.w_ext_in_ae
if not self.lr_opt:
model_segm = get_model()
find_learning_rate(model_segm, self.flow_segm, lr1=1e0)
for i_fold in range(6):
print(f'i_fold = {i_fold}')
model_segm = get_model()
n_segm = NeuralNet(model_segm, w_ext=w_ext)
train_data_i = self.k_fold_train_data.k_split_i(i_fold)
img_y_tr = train_data_i.get_y_train()
img_y_te = train_data_i.get_y_test()
flow_tr = get_flow(self.img_x,
img_y_tr,
w_patch=self.w_patch,
w_ext_in=w_ext)
flow_te = get_flow(self.img_x,
img_y_te,
w_patch=self.w_patch,
w_ext_in=w_ext)
info = get_info()
for epoch in range(self.epochs):
n_segm.train(flow_tr, flow_te, epochs=1, verbose=2, info=info)
y_pred = n_segm.predict(self.img_x)
thresh_single = optimal_test_thresh_equal_distribution(
img_y_all, y_pred)
data_single_i = {'k': self.k, 'i_fold': i_fold, 'epoch': epoch}
data_single_i.update(
foo_performance(img_y_te, y_pred, thresh_single))
lst_data_single = [data_single_i]
df_single = pd.DataFrame(lst_data_single)
pandas_save(path_single, df_single, append=True)
return
elif dataset_name == '19_hand_SE':
train_data = get_19SE_shuang(mod=mod)
else:
train_data = get_13botleftshuang(mod=mod)
# TODO normalise inputs This seems to be super important...
# train_data.x = (1/255. * train_data.x).astype(np.float16)
# train_data.x = (255. * train_data.x).astype(np.float16)
x, y_tr, x_te, y_te = get_training_data(train_data)
# To get w_ext
w_ext = neuralNet0(mod=mod, k=1, verbose=1).w_ext
flow_tr = get_flow(x[0], y_tr[0],
w_patch=10, # Comes from 10
w_ext_in=w_ext
)
flow_te = get_flow(x_te[0], y_te[0],
w_patch=10, # Comes from 10
w_ext_in=w_ext
)
b = 1
class_weight = (1, 1)
if b:
# Balance the data
class_weight_tr = get_class_weights(flow_tr)
class_weight = tuple(c_i * c_j for c_i, c_j in zip(class_weight, class_weight_tr))