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)