def validate(data_type, model, seq_length=60, saved_model=None,
class_limit=None, image_shape=None):
batch_size = 16
# Get the data and process it.
if image_shape is None:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit
)
else:
data = DataSet(
seq_length=seq_length,
class_limit=class_limit,
image_shape=image_shape
)
val_generator = data.frame_generator(batch_size, 'test', data_type)
# Get the model.
rm = ResearchModels(len(data.classes), model, seq_length, saved_model)
# Evaluate!
results = rm.model.evaluate_generator(
generator=val_generator,
val_samples=15,
use_multiprocessing=True,
workers=1)
print(results)
print(rm.model.metrics_names)
#val_generator = data.frame_generator(1,'test', data_type)
# Get the model.
rm = ResearchModels(len(data.classes), model, seq_length, saved_model)
# Evaluate!
scores=np.zeros([14])
total=np.zeros([14])
val_trues=[]
val_preds=[]
for X,y in data.gen_test('test', data_type):
results = rm.model.predict(X)
predicted=np.argmax(results, axis=-1)
idx=np.where(np.array(y)==1)
true_label=idx[1]
print(true_label)
total[true_label]=total[true_label]+1
print(len(predicted))
print(len(true_label))
if predicted[0]==true_label[0]:
scores[true_label]=scores[true_label]+1
#val_preds = np.argmax(results, axis=-1)
print('Confusion Matrix')
tn, fp, fn, tp =confusion_matrix(true_label, predicted).ravel()
print("\n *** Confusion matrix**")
print(tp)
print(tn)
print(fp)
print(fn)
print('\n****************')
print(classification_report(true_label, predicted))
print(scores)
print('\n****************')
print(total)
