def conf_thresholding(data_dir, save_dir):
# collect all trajectories
tracker_id_score = dict()
eval_dir = os.path.join(data_dir, 'data')
seq_list, num_seq = load_list_from_folder(eval_dir)
for seq_file in seq_list:
seq_data, num_line = load_txt_file(seq_file)
for data_line in seq_data:
data_split = data_line.split(' ')
score_tmp = float(data_split[-1])
id_tmp = int(data_split[1])
if id_tmp not in tracker_id_score.keys():
tracker_id_score[id_tmp] = list()
tracker_id_score[id_tmp].append(score_tmp)
# collect the ID to remove based on the confidence
to_delete_id = list()
for track_id, score_list in tracker_id_score.items():
average_score = sum(score_list) / float(len(score_list))
if average_score < score_threshold:
to_delete_id.append(track_id)
# remove the ID in the data folder
save_dir_tmp = os.path.join(save_dir, 'data'); mkdir_if_missing(save_dir_tmp)
for seq_file in seq_list:
seq_name = fileparts(seq_file)[1]
seq_file_save = os.path.join(save_dir_tmp, seq_name+'.txt'); seq_file_save = open(seq_file_save, 'w')
seq_data, num_line = load_txt_file(seq_file)
for data_line in seq_data:
data_split = data_line.split(' ')
id_tmp = int(data_split[1])
if id_tmp not in to_delete_id:
seq_file_save.write(data_line + '\n')
seq_file_save.close()
# remove the ID in the trk with id folder
trk_id_dir = os.path.join(data_dir, 'trk_withid')
seq_dir_list, num_seq = load_list_from_folder(trk_id_dir)
save_dir_tmp = os.path.join(save_dir, 'trk_withid')
for seq_dir in seq_dir_list:
frame_list, num_frame = load_list_from_folder(seq_dir)
seq_name = fileparts(seq_dir)[1]
save_frame_dir = os.path.join(save_dir_tmp, seq_name); mkdir_if_missing(save_frame_dir)
for frame in frame_list:
frame_index = fileparts(frame)[1]
frame_file_save = os.path.join(save_frame_dir, frame_index+'.txt'); frame_file_save = open(frame_file_save, 'w')
frame_data, num_line = load_txt_file(frame)
for data_line in frame_data:
data_split = data_line.split(' ')
id_tmp = int(data_split[-1])
if id_tmp not in to_delete_id:
frame_file_save.write(data_line + '\n')
frame_file_save.close()
def test_cocoeval():
engine = data_engine.Movie2Caption('attention', 'youtube2text',
video_feature='googlenet',
mb_size_train=20,
mb_size_test=20,
maxlen=50, n_words=20000,
n_frames=20, outof=None)
samples_valid = utils.load_txt_file('./model_files/valid_samples.txt')
samples_test = utils.load_txt_file('./model_files/test_samples.txt')
samples_valid = [sample.strip() for sample in samples_valid]
samples_test = [sample.strip() for sample in samples_test]
samples_valid = build_sample_pairs(samples_valid, engine.valid_ids)
samples_test = build_sample_pairs(samples_test, engine.test_ids)
valid_score, test_score = score_with_cocoeval(samples_valid, samples_test, engine)
print valid_score, test_score
def process_document(path,
vocab,
title_start="========,",
forbidden_start="***LIST***",
test=False,
ssplit=True):
print("ssplit: " + str(ssplit))
lines = ([
l for l in utils.load_lines(path) if not l.startswith(forbidden_start)
]) if ssplit else (sentence_split(utils.load_txt_file(path)))
stride = 1 if test else config.sent_stride
lab_lines = []
lines_txt = []
for i in range(len(lines)):
if lines[i].startswith(title_start):
continue
if (i - 1) >= 0 and lines[i - 1].startswith(title_start):
lab_lines.append((lines[i], 1))
else:
lab_lines.append((lines[i], 0))
lines_txt.append(lines[i])
raw_blocks = []
i = 0
while i < len(lab_lines):
block = lab_lines[i:i + config.sent_window]
if len(block) < config.sent_window:
block.extend([(config.fake_sent, 0)] *
(config.sent_window - len(block)))
raw_blocks.append(block)
i += stride
if not test:
random.shuffle(raw_blocks)
raw_blocks = raw_blocks[:int(config.perc_blocks_train *
len(raw_blocks))]
doc_recs = []
for rb in raw_blocks:
records = create_one_instance(rb, lines_txt, vocab)
doc_recs.extend(records)
return doc_recs, len(raw_blocks), raw_blocks if test else None
def classify():
IMAGE = '/dl1/data/projects/imagenet/valid/'
LABELS = '/dl1/data/projects/imagenet/val.txt'
MEAN = '/dl1/data/projects/imagenet/ilsvrc_2012_mean.npy'
EXT = 'JPEG'
preprocessor = utils.VGGImageFuncs()
'''build theano fn'''
x = T.ftensor4('images')
model = build_model(x)
y = lasagne.layers.get_output(model['prob'], deterministic=True)
params = lasagne.layers.get_all_params(model['prob'], trainable=True)
classify_fn = theano.function([x], y)
'''perform classification'''
files = glob.glob(IMAGE + '/*.' + EXT)
files = utils.sort_by_numbers_in_file_name(files)
labels = utils.load_txt_file(LABELS)
labels = [int((label.split(' ')[-1]).strip()) for label in labels]
# go through minibatches
idx = utils.generate_minibatch_idx(len(files), 64)
TOP1s = []
TOP5s = []
for i, index in enumerate(idx):
t0 = time.time()
current = [files[j] for j in index]
gts = np.asarray([labels[j] for j in index])
#inputs =[load_image(im_f) for im_f in current]
inputs = preprocessor.preprocess(current)
import ipdb
ipdb.set_trace()
probs = classify_fn(inputs) # (m, 1000, 1, 1)
probs = np.squeeze(probs)
predictions = probs.argsort()[:, ::-1][:, :5]
for pred, gt in zip(predictions, gts):
TOP1 = pred[0] == gt
TOP5 = gt in pred
TOP1s.append(TOP1)
TOP5s.append(TOP5)
print '%d / %d minibatches, acu TOP1 %.4f, TOP5 %.4f, used %.2f' % (
i, len(idx), np.mean(TOP1s) * 100, np.mean(TOP5s) * 100,
time.time() - t0)