optimizer=optimizer,
iterator_seed=1,
cropped=True)
print('compiled')
num_epochs = 30
model.fit(train_set.X,
train_set.y,
epochs=num_epochs,
batch_size=64,
scheduler='cosine',
input_time_length=input_time_length)
print(model.epochs_df)
model.network.eval()
print(model.predict(test_set.X))
scores = model.evaluate(test_set.X, test_set.y)
Accuracy = 1 - scores['misclass']
print('Accuracy (%) :', Accuracy)
# save key values
Accuracies[count, CV] = Accuracy
Losses[count, :] = model.epochs_df['train_loss']
#th.save({'Acc':Accuracies,'Losses': Losses}, var_save_path)
print('Overall Acc Subject {}: {}'.format(i,
np.mean(Accuracies[count])))
count += 1
print('last_step')
test_set = SignalAndTarget(X[(trainingSampleSize + valudationSampleSize):],
y=y[(trainingSampleSize + valudationSampleSize):])
eval = model.evaluate(test_set.X, test_set.y)
print(eval)
print(eval['misclass'])
np.save(
"finetuneCrossSubjects\{}-{}-singleSubjectNum{}-2.5sec-{}epoches-testSetMisclass"
.format(model_type, train_type, single_subject_num,
epoches), eval['misclass'])
from sklearn.metrics import confusion_matrix
try:
print("prediction")
y_pred = model.predict(test_set.X)
print(y_pred)
print("real labels")
print(test_set.y)
confusion_matrix = confusion_matrix(test_set.y, y_pred)
print(confusion_matrix)
except:
try:
y_pred = model.predict_classes(test_set.X)
print(y_pred)
print("real labels")
print(test_set.y)
confusion_matrix = confusion_matrix(test_set.y, y_pred)
print(confusion_matrix)
except:
print("predict_classes method failed")