def main(args):
timer = Timer()
print('create images...')
timer.reset()
# 入力画像の生成
x = create(args.other_path, args.human_path, args.background_path,
args.obj_size, args.img_size, args.obj_num, args.human_num,
args.img_num)
timer.view()
print('save images...')
timer.reset()
# 保存するパスを取得
w_path = [
F.getFilePath(args.out_path,
GET.datetimeSHA(GET.randomStr(10), str_len=12), '.jpg')
for i in x
]
# 画像を保存する
[cv2.imwrite(w, i) for i, w in zip(x, w_path)]
timer.view()
print('save param...')
timer.reset()
# 画像の生成に使用したパラメータを保存する
F.dict2json(args.out_path, 'dataset', F.args2dict(args))
timer.view()
def main(args):
print('create images...')
x, y = create(args.other_path, args.human_path, args.background_path,
args.obj_size, args.img_size, args.obj_num, args.human_num,
args.img_num)
# 画像の並び順をシャッフルするための配列を作成する
# compとrawの対応を崩さないようにシャッフルしなければならない
# また、train_sizeで端数を切り捨てる
# データをint8からfloat16に変えるとデータ数が大きくなるので注意
print('shuffle images...')
dtype = np.float16
shuffle = np.random.permutation(range(len(x)))
train_size = int(len(x) * args.train_per_all)
train_x = IMG.imgs2arr(x[shuffle[:train_size]], dtype=dtype)
train_y = IMG.imgs2arr(y[shuffle[:train_size]], dtype=dtype)
test_x = IMG.imgs2arr(x[shuffle[train_size:]], dtype=dtype)
test_y = IMG.imgs2arr(y[shuffle[train_size:]], dtype=dtype)
print('train x/y:{0}/{1}'.format(train_x.shape, train_y.shape))
print('test x/y:{0}/{1}'.format(test_x.shape, test_y.shape))
print('save param...')
F.dict2json(args.out_path, 'dataset', F.args2dict(args))
# 生成したデータをnpz形式でデータセットとして保存する
# ここで作成したデータの中身を確認する場合はnpz2jpg.pyを使用するとよい
print('save npz...')
saveNPZ(train_x, train_y, 'train', args.out_path, args.img_size)
saveNPZ(test_x, test_y, 'test', args.out_path, args.img_size)
def writeJson(self):
param = {
'true value': self.trueVal,
'ave color': self.cap.ave_color,
'exc shape': self.cap.exc_shape,
}
print(param)
F.dict2json(self.out_path, 'param', param)
def main(args):
# フォント画像の読み込みと分割する
print('read and split images...')
fonts, _ = I.cnv.splitSQN(I.io.readN(args.font, 3), args.font_size)
print(fonts.shape)
param = F.args2dict(args)
param['shape'] = fonts.shape
# 正解画像の生成と保存
max_folder = 4000
proc = 7
print('create and save images...')
for i in range(0, args.img_num, max_folder):
num = np.min([max_folder, args.img_num - i])
[
cv2.imwrite(getPath(args.out_path, i // max_folder), j) for j in
createN(fonts, args.img_size, args.font_num, num, processes=proc)
]
print('save param...')
F.dict2json(args.out_path, 'dataset', param)
def main(args):
# 各種データをユニークな名前で保存するために時刻情報を取得する
exec_time = GET.datetimeSHA()
# Set up a neural network to train
# Classifier reports softmax cross entropy loss and accuracy at every
# iteration, which will be used by the PrintReport extension below.
# 活性化関数を取得する
actfun1 = GET.actfun(args.actfun1)
actfun2 = GET.actfun(args.actfun2)
# モデルを決定する
if args.network == 0:
from Lib.network import JC_DDUU as JC
else:
from Lib.network2 import JC_UDUD as JC
model = L.Classifier(
JC(n_unit=args.unit, layer=args.layer_num, rate=args.shuffle_rate,
actfun1=actfun1, actfun2=actfun2, dropout=args.dropout,
view=args.only_check),
lossfun=GET.lossfun(args.lossfun)
)
# Accuracyは今回使用しないのでFalseにする
# もしも使用したいのであれば、自分でAccuracyを評価する関数を作成する必要あり？
model.compute_accuracy = False
# Setup an optimizer
optimizer = GET.optimizer(args.optimizer).setup(model)
# Load dataset
train, test, _ = GET.imgData(args.in_path)
train = ResizeImgDataset(train, args.shuffle_rate)
test = ResizeImgDataset(test, args.shuffle_rate)
# predict.pyでモデルを決定する際に必要なので記憶しておく
model_param = F.args2dict(args)
model_param['shape'] = train[0][0].shape
train_iter = chainer.iterators.SerialIterator(train, args.batchsize)
test_iter = chainer.iterators.SerialIterator(test, args.batchsize,
repeat=False, shuffle=False)
# Set up a trainer
updater = training.StandardUpdater(
train_iter, optimizer, device=args.gpu_id
)
trainer = training.Trainer(
updater, (args.epoch, 'epoch'), out=args.out_path
)
# Evaluate the model with the test dataset for each epoch
trainer.extend(extensions.Evaluator(test_iter, model, device=args.gpu_id))
# Dump a computational graph from 'loss' variable at the first iteration
# The "main" refers to the target link of the "main" optimizer.
trainer.extend(
extensions.dump_graph('main/loss', out_name=exec_time + '_graph.dot')
)
# Take a snapshot for each specified epoch
frequency = args.epoch if args.frequency == -1 else max(1, args.frequency)
trainer.extend(
extensions.snapshot(filename=exec_time + '_{.updater.epoch}.snapshot'),
trigger=(frequency, 'epoch')
)
# Write a log of evaluation statistics for each epoch
trainer.extend(extensions.LogReport(log_name=exec_time + '.log'))
# trainer.extend(extensions.observe_lr())
# Save two plot images to the result dir
if args.plot and extensions.PlotReport.available():
trainer.extend(
PlotReportLog(['main/loss', 'validation/main/loss'],
'epoch', file_name='loss.png')
)
# trainer.extend(
# PlotReportLog(['lr'],
# 'epoch', file_name='lr.png', val_pos=(-80, -60))
# )
# Print selected entries of the log to stdout
# Here "main" refers to the target link of the "main" optimizer again, and
# "validation" refers to the default name of the Evaluator extension.
# Entries other than 'epoch' are reported by the Classifier link, called by
# either the updater or the evaluator.
trainer.extend(extensions.PrintReport([
'epoch',
'main/loss',
'validation/main/loss',
# 'lr',
'elapsed_time'
]))
# Print a progress bar to stdout
trainer.extend(extensions.ProgressBar())
# Resume from a snapshot
if args.resume:
chainer.serializers.load_npz(args.resume, trainer)
# Set pruning
# http://tosaka2.hatenablog.com/entry/2017/11/17/194051
masks = pruning.create_model_mask(model, args.pruning, args.gpu_id)
trainer.extend(pruning.pruned(model, masks))
# Make a specified GPU current
if args.gpu_id >= 0:
chainer.backends.cuda.get_device_from_id(args.gpu_id).use()
# Copy the model to the GPU
model.to_gpu()
chainer.global_config.autotune = True
else:
model.to_intel64()
# predict.pyでモデルのパラメータを読み込むjson形式で保存する
if args.only_check is False:
F.dict2json(args.out_path, exec_time + '_train', model_param)
# Run the training
trainer.run()
# 最後にモデルを保存する
# スナップショットを使ってもいいが、
# スナップショットはファイルサイズが大きい
chainer.serializers.save_npz(
F.getFilePath(args.out_path, exec_time, '.model'),
model
)