mean = app.session.run(app.ts.final_mean)
print(mean)
msd = app.session.run(app.ts.final_msd)
print(msd)
std = np.sqrt(msd - mean**2)
print(std)
vec = np.random.normal(mean, std, [sample, len(std)])
images = app.session.run(app.ts.y, {app.ts.vec: vec}) # [-1, 28, 28]
# 将所有图片做成一张图片，每行20张小图
images = np.reshape(images, [-1, col, 28, 28]) # [-1, 20, 28, 28]
images = np.transpose(images, [0, 2, 1, 3]) # [-1, 28, 20, 28]
images = np.reshape(images, [-1, col * 28]) # [-1, 28, 20 * 28]
# images = np.transpose(images, [2, 0, 1]) # [20 * 28, -1, 28]
# images = np.reshape(images, [col * 28, -1]) # [20 * 28, -1]
# images = np.transpose(images, [1, 0]) # [-1, 20 * 28]
cv2.imwrite(path, images * 255)
if __name__ == '__main__':
tf.disable_eager_execution()
tf.reset_default_graph()
config = MyConfig()
ds = read_data_sets(config.simple_path)
app = myf.App(config)
with app:
app.train(ds_train=MyDS(ds.train, config),
ds_validation=MyDS(ds.validation, config))
# predict(app, config.batch_size, config.image_path, config.col)
class MyDS:
def __init__(self, ds, config):
self.ds = ds
self.lr = config.lr
self.num_examples = ds.num_examples
def next_batch(self, batch_size):
xs, ys = self.ds.next_batch(batch_size)
return xs, self.lr
class App:
def __init__(self):
pass
if __name__ == '__main__':
cfg = MyConfig()
cfg.from_cmd()
print('_'*20)
print(cfg)
dss = read_data_sets(cfg.sample_path)
app = myf.App(cfg)
with app:
app.train(MyDS(dss.train, cfg), MyDS(dss.validation, cfg))
mean = app.session.run(app.ts.final_mean)
print(mean)
msd = app.session.run(app.ts.final_msd) # 二阶原点矩
print(np.sqrt(msd - mean**2))