def class_to_int():
class_to_int = {}
class_count = 0
for class_dir in os.listdir(FRAME_DATA_PATH):
class_dir_path = os.path.join(FRAME_DATA_PATH, class_dir)
if not os.path.isdir(class_dir_path):
continue
class_to_int[class_dir] = class_count
class_count += 1
compressed_pickle('class_to_int.pickle', class_to_int)
def main():
cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=CHECKPOINT_PATH,
save_best_only=True, save_weights_only=False, verbose=1)
history_checkpoint = LossHistory()
labels = decompress_pickle('labels.pickle.pbz2')
partition = decompress_pickle('partition.pickle.pbz2')
training_generator = OurGenerator(partition['train'], labels)
validation_generator = OurGenerator(partition['val'], labels)
model = get_model()
history = model.fit_generator(generator=training_generator,
validation_data=validation_generator,
epochs=10,
callbacks=[cp_callback, history_checkpoint])
model.save('models/ours_3_10epochs_model')
compressed_pickle('history/ours_3_10epochs.pickle', history.history)
def setupInput():
class_to_int = decompress_pickle('class_to_int.pickle.pbz2')
labels = {}
ids = []
counter = 0
for class_dir in os.listdir(FRAME_DATA_PATH):
class_dir_path = os.path.join(FRAME_DATA_PATH, class_dir)
if not os.path.isdir(class_dir_path):
continue
label = class_to_int[class_dir]
all_videos = os.listdir(class_dir_path)
num_to_choose = VIDEOS_PER_CLASS
if len(all_videos) < VIDEOS_PER_CLASS:
num_to_choose = len(all_videos)
chosen_videos = random.choices(all_videos, k = num_to_choose)
remaining_videos = list(set(all_videos) - set(chosen_videos))
for video_dir in chosen_videos:
video_dir_path = os.path.join(class_dir_path, video_dir)
if not os.path.isdir(video_dir_path):
continue
frames = []
all_frames = os.listdir(video_dir_path)
num_frames_choose = FRAMES_PER_VIDEO
if len(all_frames) < FRAMES_PER_VIDEO:
num_frames_choose = len(all_frames)
chosen_frames_indices = np.linspace(0, len(all_frames) - 1, num = num_frames_choose)
for frame_index in chosen_frames_indices:
frame_index = math.floor(frame_index)
frame_file = all_frames[frame_index]
frame_path = os.path.join(video_dir_path, frame_file)
if not os.path.isfile(frame_path):
continue
image = Image.open(frame_path)
image = normalize(image)
frames.append(image)
id = 'id-' + str(counter)
ids.append(id)
compressed_pickle('new_inputs/' + id + '.pickle', frames)
counter += 1
labels[id] = label
print('saved inputs for ' + class_dir)
compressed_pickle('new_remaining/' + class_dir + '.pickle', remaining_videos)
training_ids = random.choices(ids, k = int(np.floor(len(ids) * 2 / 3)))
rest = list(set(ids) - set(training_ids))
val_ids = random.choices(rest, k = int(np.floor(len(rest) * 2 / 3)))
test_ids = list(set(rest) - set(val_ids))
partition = {'train': training_ids, 'val': val_ids, 'test': test_ids}
compressed_pickle('partition.pickle', partition)
compressed_pickle('labels.pickle', labels)
file = 'reports.pbz2'
open_reports = True
n_trials = 1000
if not os.path.isfile(file): # si no están los experimentos guardados
probs = 1 / np.logspace(0, 4, 10)
lengths = np.logspace(1, 5, 10, dtype=int)
experiments = []
for n in tqdm(lengths, ncols=100):
for p in probs:
current_experiment = Experiment(p, n, n_trials)
current_experiment.make_report()
experiments.append(current_experiment)
reports = {experiment.__repr__(): experiment.report for experiment in experiments}
compressed_pickle(file, reports)
open_reports = False
del experiments
if open_reports: # si la variable "reports" no está asignada
reports = decompress_pickle(file)
percentage_more_than_one = []
for name, report in reports.items():
plot_confussion_matrix(report, title=name, save_as=f'cms/{name}')
plt.close("all")
error_percentage = []
for _, report in reports.items():
error_percentage.append(percentages_erros(report))