benset.get_dataset_annotations(), batch_size,
num_frames)
#benset_seq = BatchLoader(benset, benset.get_dataset_keys(),benset.get_dataset_annotations(),batch_size,num_frames, mode=1, random_hflip=1, random_brightness=1, random_channel_shift=0, random_zoom=1, random_subsampling=1, random_rot=1, random_blur=1)
from sklearn.metrics import confusion_matrix
y_actu = []
y_pred = []
from collections import Counter
predictions = []
wrong = [0, 0, 0, 0]
while True:
x, y = benset_test.__next__()
if x is None:
break
prediction = full_model.predict(x)
pred_action = np.argmax(prediction[11])
annot_action = np.argmax(y[0])
y_actu.append(annot_action)
y_pred.append(pred_action)
if pred_action == annot_action:
predictions.append(1)
else:
trainer = MultiModelTrainer([models[1]], [benset_train_batchloader],
workers=6,
print_full_losses=True)
trainer.train(40,
steps_per_epoch=steps_per_epoch,
initial_epoch=3,
end_of_epoch_callback=fcallback)
y_actu = []
y_pred = []
predictions = []
printcn(OKBLUE, 'Validation on Benset')
for i in range(len(benset_dataloader.get_test_data_keys())):
#printc(OKBLUE, '%04d/%04d\t' % (i, len(val_data_keys)))
x, y = benset_test_batchloader.__next__()
prediction = full_model.predict(x)
pred_action = np.argmax(prediction[11])
annot_action = np.argmax(y[0])
y_actu.append(annot_action)
y_pred.append(pred_action)
if pred_action == annot_action:
predictions.append(1)
else:
predictions.append(0)
accuracy = 100.0 / len(predictions) * Counter(predictions)[1]
