image_preprocess_config = {
'data_format': 'channels_last', # 'channels_last' ,'channels_first'
'target_size': [320, 320],
'shorter_side': 480,
'is_random_crop': False,
'random_horizontal_flip': 0.5, # <=1.0
'random_vertical_flip': 0., # < 1.0
'pad_truth_to': 60 # >=2 , >= the maximum of number of bbox per image + 1
}
data = [
'./test/test_00000-of-00005.tfrecord',
'./test/test_00001-of-00005.tfrecord'
]
train_gen = voc_utils.get_generator(data, batch_size, buffer_size,
image_preprocess_config)
trainset_provider = {
'data_shape': [320, 320, 3],
'num_train': 5000,
'num_val': 0, # not used
'train_generator': train_gen,
'val_generator': None # not used
}
refinedet = net.RefineDet320(config, trainset_provider)
# refinedet.load_weight('./refinedet320/test-64954')
for i in range(epochs):
print('-' * 25, 'epoch', i, '-' * 25)
if i in reduce_lr_epoch:
lr = lr / 10.
print('reduce lr, lr=', lr, 'now')
mean_loss = refinedet.train_one_epoch(lr)
'output_shape': [384, 384],
'zoom_size': [400, 400],
'crop_method': 'random',
'flip_prob': [0., 0.5],
'fill_mode': 'BILINEAR',
'keep_aspect_ratios': False,
'constant_values': 0.,
'color_jitter_prob': 0.5,
'rotate': [0.5, -10., 10.],
'pad_truth_to': 60,
}
data = os.listdir('./voc2007/')
data = [os.path.join('./voc2007/', name) for name in data]
train_gen = voc_utils.get_generator(data, batch_size, buffer_size,
image_augmentor_config)
trainset_provider = {
'data_shape': [384, 384, 3],
'num_train': 5011,
'num_val': 0, # not used
'train_generator': train_gen,
'val_generator': None # not used
}
centernet = net.CenterNet(config, trainset_provider)
# centernet.load_weight('./centernet/test-8350')
# centernet.load_pretrained_weight('./centernet/test-8350')
for i in range(epochs):
print('-' * 25, 'epoch', i, '-' * 25)
if i in reduce_lr_epoch:
lr = lr / 10.
print('reduce lr, lr=', lr, 'now')
def run(j, learn_rate, test_net, init_list, mean_loss):
if j % resize_num == 0 and j != 0:
global input_shape
test_net.save_section_weight('latest', './yolo2/latest/latest',
mean_loss, j)
test_net.sess.close()
init_list.append(test_net.train_initializer)
index = random.randint(0, 9)
input_shape = [shape[index], shape[index], 3]
print('Resize: ' + str(input_shape))
new_factor = float(input_shape[0] / 320)
test_net.data_shape = input_shape
priors = [[round(0.42 * new_factor, 3),
round(0.72 * new_factor, 3)],
[round(0.92 * new_factor, 3),
round(1.63 * new_factor, 3)],
[round(1.78 * new_factor, 3),
round(3.2 * new_factor, 3)],
[round(3.68 * new_factor, 3),
round(5.2 * new_factor, 3)],
[round(7.825 * new_factor, 3),
round(7.72 * new_factor, 3)]]
priors = tf.convert_to_tensor(priors, dtype=tf.float32)
test_net.priors = tf.reshape(priors, [1, 1, test_net.num_priors, 2])
image_augmentor_config['output_shape'] = [
input_shape[0], input_shape[1]
]
train_gen1 = voc_utils.get_generator(data,
batch_size * config['num_gpu'],
buffer_size,
image_augmentor_config)
test_net.train_generator = train_gen1
test_net.train_initializer, test_net.train_iterator = test_net.train_generator
test_net.sess = tf.Session()
test_net.sess.run(tf.global_variables_initializer())
test_net.sess.run(init_list)
test_net.define_inputs()
for file in os.listdir('./yolo2/latest/'):
if (file.split('.')[0]).startswith('latest-backone'):
global backone
backone = file.split('.')[0]
elif (file.split('.')[0]).startswith('latest-head'):
global head
head = file.split('.')[0]
test_net.latest_weight_saver1.restore(test_net.sess,
'./yolo2/latest/' + str(backone))
test_net.latest_weight_saver2.restore(test_net.sess,
'./yolo2/latest/' + str(head))
print('-' * 25, 'epoch', j, '-' * 25)
if j == 500:
learn_rate = learn_rate / 5.
print('reduce lr, lr=', learn_rate, 'now')
if j == 800:
learn_rate = learn_rate / 2.
print('reduce lr, lr=', lr, 'now')
mean_loss = test_net.train_one_epoch(learn_rate, j)
print('>> mean loss', mean_loss)
test_net.save_section_weight('best', './yolo2/best/best', mean_loss,
j) # 'latest', 'best'
