def test_step(n_class, top_k_percent, att_gate, att_only, mil_ins, mut_ex,
m_clam_op, imf_norm_op, c_model, dim_compress_features,
test_path, result_path, result_file_name, n_test_steps):
start_time = time.time()
slide_true_label = list()
slide_predict_label = list()
sample_names = list()
test_sample_list = os.listdir(test_path)
test_sample_list = random.sample(test_sample_list, len(test_sample_list))
for i in test_sample_list:
print('>', end="")
single_test_data = test_path + i
img_features, slide_label = get_data_from_tf(single_test_data,
imf_norm_op=imf_norm_op)
predict_slide_label = m_test_per_sample(
n_class=n_class,
top_k_percent=top_k_percent,
att_gate=att_gate,
att_only=att_only,
m_clam_op=m_clam_op,
mil_ins=mil_ins,
mut_ex=mut_ex,
c_model=c_model,
dim_compress_features=dim_compress_features,
img_features=img_features,
slide_label=slide_label,
n_test_steps=n_test_steps)
slide_true_label.append(slide_label)
slide_predict_label.append(predict_slide_label)
sample_names.append(i)
test_results = pd.DataFrame(list(
zip(sample_names, slide_true_label, slide_predict_label)),
columns=[
'Sample Names', 'Slide True Label',
'Slide Predict Label'
])
test_results.to_csv(os.path.join(result_path, result_file_name),
sep='\t',
index=False)
tn, fp, fn, tp = sklearn.metrics.confusion_matrix(
slide_true_label, slide_predict_label).ravel()
test_tn = int(tn)
test_fp = int(fp)
test_fn = int(fn)
test_tp = int(tp)
test_sensitivity = round(test_tp / (test_tp + test_fn), 2)
test_specificity = round(test_tn / (test_tn + test_fp), 2)
test_acc = round(
(test_tp + test_tn) / (test_tn + test_fp + test_fn + test_tp), 2)
fpr, tpr, thresholds = sklearn.metrics.roc_curve(slide_true_label,
slide_predict_label,
pos_label=1)
test_auc = round(sklearn.metrics.auc(fpr, tpr), 2)
test_run_time = time.time() - start_time
template = '\n Test Accuracy: {}, Test Sensitivity: {}, Test Specificity: {}, Test Running Time: {}'
print(
template.format(f"{float(test_acc):.4%}",
f"{float(test_sensitivity):.4%}",
f"{float(test_specificity):.4%}",
"--- %s mins ---" % int(test_run_time / 60)))
def val_step(c_model, val_path, imf_norm_op, i_loss_name, b_loss_name, mut_ex,
n_class, c1, c2, top_k_percent, batch_size, batch_op):
i_loss_func, b_loss_func = load_loss_func(i_loss_func_name=i_loss_name,
b_loss_func_name=b_loss_name)
loss_t = list()
loss_i = list()
loss_b = list()
slide_true_label = list()
slide_predict_label = list()
val_sample_list = os.listdir(val_path)
val_sample_list = random.sample(val_sample_list, len(val_sample_list))
for i in val_sample_list:
print('=', end="")
single_val_data = val_path + i
img_features, slide_label = get_data_from_tf(tf_path=single_val_data,
imf_norm_op=imf_norm_op)
img_features = random.sample(
img_features,
len(img_features)) # follow the training loop, see details there
if batch_op:
if batch_size < len(img_features):
I_Loss, B_Loss, T_Loss, predict_slide_label = b_val(
batch_size=batch_size,
top_k_percent=top_k_percent,
n_samples=len(img_features),
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
else:
I_Loss, B_Loss, T_Loss, predict_slide_label = nb_val(
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
else:
I_Loss, B_Loss, T_Loss, predict_slide_label = nb_val(
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
loss_t.append(float(T_Loss))
loss_i.append(float(I_Loss))
loss_b.append(float(B_Loss))
slide_true_label.append(slide_label)
slide_predict_label.append(predict_slide_label)
tn, fp, fn, tp = sklearn.metrics.confusion_matrix(
slide_true_label, slide_predict_label).ravel()
val_tn = int(tn)
val_fp = int(fp)
val_fn = int(fn)
val_tp = int(tp)
val_sensitivity = round(val_tp / (val_tp + val_fn), 2)
val_specificity = round(val_tn / (val_tn + val_fp), 2)
val_acc = round((val_tp + val_tn) / (val_tn + val_fp + val_fn + val_tp), 2)
fpr, tpr, thresholds = sklearn.metrics.roc_curve(slide_true_label,
slide_predict_label,
pos_label=1)
val_auc = round(sklearn.metrics.auc(fpr, tpr), 2)
val_loss = statistics.mean(loss_t)
val_ins_loss = statistics.mean(loss_i)
val_bag_loss = statistics.mean(loss_b)
return val_loss, val_ins_loss, val_bag_loss, val_tn, val_fp, val_fn, val_tp, val_sensitivity, val_specificity, \
val_acc, val_auc
def train_step(c_model, train_path, imf_norm_op, i_wd_op_name, b_wd_op_name,
a_wd_op_name, i_optimizer_name, b_optimizer_name,
a_optimizer_name, i_loss_name, b_loss_name, mut_ex, n_class, c1,
c2, i_learn_rate, b_learn_rate, a_learn_rate, i_l2_decay,
b_l2_decay, a_l2_decay, top_k_percent, batch_size, batch_op):
i_optimizer, b_optimizer, a_optimizer = load_optimizers(
i_wd_op_name=i_wd_op_name,
b_wd_op_name=b_wd_op_name,
a_wd_op_name=a_wd_op_name,
i_optimizer_name=i_optimizer_name,
b_optimizer_name=b_optimizer_name,
a_optimizer_name=a_optimizer_name,
i_learn_rate=i_learn_rate,
b_learn_rate=b_learn_rate,
a_learn_rate=a_learn_rate,
i_l2_decay=i_l2_decay,
b_l2_decay=b_l2_decay,
a_l2_decay=a_l2_decay)
i_loss_func, b_loss_func = load_loss_func(i_loss_func_name=i_loss_name,
b_loss_func_name=b_loss_name)
loss_total = list()
loss_ins = list()
loss_bag = list()
slide_true_label = list()
slide_predict_label = list()
train_sample_list = os.listdir(train_path)
train_sample_list = random.sample(train_sample_list,
len(train_sample_list))
for i in train_sample_list:
print('=', end="")
single_train_data = train_path + i
img_features, slide_label = get_data_from_tf(tf_path=single_train_data,
imf_norm_op=imf_norm_op)
# shuffle the order of img features list in order to reduce the side effects of randomly drop potential
# number of patches' feature vectors during training when enable batch training option
img_features = random.sample(img_features, len(img_features))
if batch_op:
if batch_size < len(img_features):
I_Loss, B_Loss, T_Loss, predict_slide_label = b_optimize(
batch_size=batch_size,
top_k_percent=top_k_percent,
n_samples=len(img_features),
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_optimizer=i_optimizer,
b_optimizer=b_optimizer,
a_optimizer=a_optimizer,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
else:
I_Loss, B_Loss, T_Loss, predict_slide_label = nb_optimize(
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_optimizer=i_optimizer,
b_optimizer=b_optimizer,
a_optimizer=a_optimizer,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
else:
I_Loss, B_Loss, T_Loss, predict_slide_label = nb_optimize(
img_features=img_features,
slide_label=slide_label,
c_model=c_model,
i_optimizer=i_optimizer,
b_optimizer=b_optimizer,
a_optimizer=a_optimizer,
i_loss_func=i_loss_func,
b_loss_func=b_loss_func,
n_class=n_class,
c1=c1,
c2=c2,
mut_ex=mut_ex)
loss_total.append(float(T_Loss))
loss_ins.append(float(I_Loss))
loss_bag.append(float(B_Loss))
slide_true_label.append(slide_label)
slide_predict_label.append(predict_slide_label)
tn, fp, fn, tp = sklearn.metrics.confusion_matrix(
slide_true_label, slide_predict_label).ravel()
train_tn = int(tn)
train_fp = int(fp)
train_fn = int(fn)
train_tp = int(tp)
train_sensitivity = round(train_tp / (train_tp + train_fn), 2)
train_specificity = round(train_tn / (train_tn + train_fp), 2)
train_acc = round(
(train_tp + train_tn) / (train_tn + train_fp + train_fn + train_tp), 2)
fpr, tpr, thresholds = sklearn.metrics.roc_curve(slide_true_label,
slide_predict_label,
pos_label=1)
train_auc = round(sklearn.metrics.auc(fpr, tpr), 2)
train_loss = statistics.mean(loss_total)
train_ins_loss = statistics.mean(loss_ins)
train_bag_loss = statistics.mean(loss_bag)
return train_loss, train_ins_loss, train_bag_loss, train_tn, train_fp, train_fn, train_tp, train_sensitivity, \
train_specificity, train_acc, train_auc