def predict_compare_regular(self):
img_y_all = self.k_fold_train_data.get_train_data_all().get_y_train()
lst_get = [
get_borders1, get_borders2, get_borders3, get_borders4,
get_borders5, get_borders6
]
img_clean = self.img_x[..., :3]
for i_fold in range(6):
y_lst = []
# Average prediction
print(f'i_fold = {i_fold}')
for k in [17, 18, 19]:
print(f'k = {k}')
for epoch in [36, 37, 38, 39, 40]:
print(f'epoch = {epoch}')
y = self.predict_regular(i_fold=i_fold, k=k, epoch=epoch)
y_lst.append(y)
y_avg = np.mean(y_lst, axis=0)
y_avg_bin = self.get_bin(y_avg)
# Performance
img_y_te = self.k_fold_train_data.k_split_i(i_fold).get_y_test()
thresh = optimal_test_thresh_equal_distribution(img_y_all, y_avg)
perf = foo_performance(img_y_te, y_avg, thresh)
# CROP
w0, w1, h0, h1 = lst_get[i_fold]()
y_avg_bin_crop = y_avg_bin[h0:h1, w0:w1]
clean_crop = img_clean[h0:h1, w0:w1, :]
y_avg_bin_transparent_crop = semi_transparant(
clean_crop, y_avg_bin_crop)
if 0:
concurrent(
[clean_crop, y_avg_bin_crop, y_avg_bin_transparent_crop])
folder_save = '/scratch/lameeus/data/ghent_altar/output/hierarchy/10_lamb/ifolds_regular_tiunet'
filename = f'_tiunet_ifold{i_fold}_jacc{perf["jaccard"]:.3f}.png'
# Save y_bin
imsave(os.path.join(folder_save, 'binpred' + filename),
y_avg_bin_crop,
b_check_duplicate=False)
# Save overlay
imsave(os.path.join(folder_save, 'overlay' + filename),
y_avg_bin_transparent_crop,
b_check_duplicate=False)
def get_bin(y_pred):
assert len(y_pred.shape) == 2
y_pred01 = np.stack([1-y_pred, y_pred], axis=-1)
thresh = optimal_test_thresh_equal_distribution(y_true, y_pred01)
print(foo_performance(y_true, y_pred01, thresh))
y_pred_bin = y_pred >= thresh
return y_pred_bin
def foo(n_segm, b=0):
y_pred = n_segm.predict(self.img_x)
thresh_single = optimal_test_thresh_equal_distribution(
self.img_y_te, y_pred)
# data_single_i = {'k': self.k,
# 'i_fold': i_fold,
# 'epoch': epoch}
print(foo_performance(self.img_y_te, y_pred, thresh_single))
img_clean = self.img_x[..., :3]
concurrent([
img_clean, y_pred[..., 1], y_pred[..., 1] >= thresh_single,
semi_transparant(img_clean, y_pred[..., 1] >= thresh_single)
])
if b:
from data.datatools import imsave
folder = '/home/lameeus/data/ghent_altar/output/hierarchy/'
info_epoch = f'_epoch{n_segm.epoch}' if n_segm.epoch > 0 else ''
filename = folder + f'13_small/pred_transfer_kfoldenc{self.fixed_enc}_ifold{self.i_fold}_avg{info_epoch}.png'
imsave(filename, y_pred[..., 1])
def predict_compare(self):
img_y_all = self.k_fold_train_data.get_train_data_all().get_y_train()
lst_get = [
get_borders1, get_borders2, get_borders3, get_borders4,
get_borders5, get_borders6
]
img_clean = self.img_x[..., :3]
for i_fold in range(6):
for i_fixed_enc in range(3):
self.fixed_enc = i_fixed_enc
y_lst = []
# Average prediction
for k in [17, 18, 19]:
for epoch in [96, 97, 98, 99, 100]:
y = self.predict(i_fold=i_fold, k=k, epoch=epoch)
y_lst.append(y)
y_avg = np.mean(y_lst, axis=0)
y_avg_bin = self.get_bin(y_avg)
# Performance
img_y_te = self.k_fold_train_data.k_split_i(
i_fold).get_y_test()
thresh = optimal_test_thresh_equal_distribution(
img_y_all, y_avg)
perf = foo_performance(img_y_te, y_avg, thresh)
# CROP
w0, w1, h0, h1 = lst_get[i_fold]()
y_avg_bin_crop = y_avg_bin[h0:h1, w0:w1]
clean_crop = img_clean[h0:h1, w0:w1, :]
y_avg_bin_transparent_crop = semi_transparant(
clean_crop, y_avg_bin_crop)
if 0:
concurrent([
clean_crop, y_avg_bin_crop, y_avg_bin_transparent_crop
])
# Save
if self.fixed_enc == 0: info_enc = 'Train'
elif self.fixed_enc == 1: info_enc = 'Fixed'
elif self.fixed_enc == 2: info_enc = 'FixedTrain'
folder_save = '/scratch/lameeus/data/ghent_altar/output/hierarchy/10_lamb/ifolds'
filename = f'_enc{info_enc}_ifold{i_fold}_jacc{perf["jaccard"]:.3f}.png'
# Save y_bin
imsave(os.path.join(folder_save, 'binpred' + filename),
y_avg_bin_crop,
b_check_duplicate=False)
# Save overlay
imsave(os.path.join(folder_save, 'overlay' + filename),
y_avg_bin_transparent_crop,
b_check_duplicate=False)
def main():
b_encoder_fixed = False
info_enc_fixed = '_enc_fixed'
folder_weights = '/scratch/lameeus/data/ghent_altar/net_weight/10lamb_kfold_pretrained'
folder_save = '/home/lameeus/data/ghent_altar/dataframes'
filename_single = f'pretrained_unet_10lamb_kfold_single'
filename_avg_pred = f'pretrained_unet_10lamb_kfold_avgpred'
folder_weights += info_enc_fixed if b_encoder_fixed else ''
filename_single += info_enc_fixed if b_encoder_fixed else ''
filename_avg_pred += info_enc_fixed if b_encoder_fixed else ''
fold_range = range(6)
# fold_range = [0, 1]
k = 10
epoch_range = range(1, 40 + 1)
w_ext_in = 28
k_fold_train_data = get_10lamb_6patches(5) # 5 is the number of modalities
train_data_all = k_fold_train_data.get_train_data_all()
img_x = train_data_all.get_x_train()
img_x = rescale0to1(img_x)
img_clean = img_x[..., :3]
img_y_all = train_data_all.get_y_train()
b_plot = False
for i_fold in fold_range:
print(i_fold)
img_y_te = k_fold_train_data.k_split_i(i_fold).get_y_test()
# Init for range epochs
lst_data_single = []
lst_data_avg_pred = []
list_y_pred = []
model = None
for epoch in np.sort(epoch_range)[::-1]:
filepath_model = os.path.join(
folder_weights, f'unet_enc_k{k}_ifold{i_fold}/w_{epoch}.h5')
model = load_model_quick(filepath_model, model=model)
n = NeuralNet(model, w_ext=w_ext_in)
y_pred = n.predict(img_x)
"""
Average out predictions
"""
list_y_pred.append(y_pred)
y_avg_pred = np.mean(list_y_pred, axis=0)
thresh_single = optimal_test_thresh_equal_distribution(
img_y_all, y_pred)
thresh_avg_pred = optimal_test_thresh_equal_distribution(
img_y_all, y_avg_pred)
y_pred_bin = np.greater_equal(y_pred[..., 1], thresh_single)
dict_perf = foo_performance(img_y_te, y_pred, thresh_single)
print(dict_perf)
if b_plot:
concurrent([
y_pred_bin, img_clean,
semi_transparant(img_clean, y_pred_bin),
semi_transparant(img_clean, img_y_te[..., 1].astype(bool))
])
data_single_i = {'k': k, 'i_fold': i_fold, 'epoch': epoch}
data_avg_pred_i = {
'k': k,
'i_fold': i_fold,
'epoch_start': epoch,
'epoch_end': max(epoch_range)
}
data_single_i.update(dict_perf)
data_avg_pred_i.update(
foo_performance(img_y_te, y_avg_pred, thresh_avg_pred))
lst_data_single.append(data_single_i)
lst_data_avg_pred.append(data_avg_pred_i)
df_single = pd.DataFrame(lst_data_single)
df_avg_pred = pd.DataFrame(lst_data_avg_pred)
path_single = os.path.join(folder_save, filename_single + '.csv')
path_avg_pred = os.path.join(folder_save, filename_avg_pred + '.csv')
pandas_save(path_single, df_single, append=True)
pandas_save(path_avg_pred, df_avg_pred, append=True)
return
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