def test():
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10)
])
predictions = model(x_train[:1]).numpy()
tf.nn.softmax(predictions).numpy()
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
loss_fn(y_train[:1], predictions).numpy()
model.compile(optimizer='adam', loss=loss_fn, metrics=['accuracy'])
if fit_flag:
with Profile(
os.path.dirname(os.path.abspath(__file__)) + '/logdir_path1'):
model.fit(x_train, y_train, epochs=1)
model.evaluate(x_test, y_test, verbose=2)
probability_model = tf.keras.Sequential(
[model, tf.keras.layers.Softmax()])
probability_model(x_test[:5])
def test3():
mnist = tf.keras.datasets.mnist
(x_train, _), (x_test, _) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
with Profile(os.path.dirname(os.path.abspath(__file__)) + '/logdir_path1'):
res = train_one_step(x_train[0:100], x_train[100:200],
x_train[200:300])
env.render()
if args.profile:
# Warm up
for step in range(hp.Learn_start+20):
action = player.act(bef_o)
aft_o,r,d,i = env.step(action)
player.step(bef_o,action,r,d,i)
if d :
bef_o = env.reset()
else:
bef_o = aft_o
if args.render :
env.render()
with Profile(f'log/{args.log_name}'):
for step in range(5):
action = player.act(bef_o)
aft_o,r,d,i = env.step(action)
player.step(bef_o,action,r,d,i)
if d :
bef_o = env.reset()
else:
bef_o = aft_o
if args.render :
env.render()
remaining_steps = total_steps - hp.Learn_start - 25
for step in range(remaining_steps):
if ((hp.Learn_start + 25 + step) % hp.Model_save) == 0 :
player.save_model()
score = evaluate_f(player, eval_env, vid_type)