def _worker(self, root_dir, parameters, device_queue):
# sleep for random seconds to avoid crowded launching
try:
time.sleep(random.uniform(0, 3))
device = device_queue.get()
if self._conf.use_gpu:
os.environ["CUDA_VISIBLE_DEVICES"] = str(device)
else:
os.environ["CUDA_VISIBLE_DEVICES"] = "" # run on cpu
from alf.utils.common import set_per_process_memory_growth
set_per_process_memory_growth()
logging.set_verbosity(logging.INFO)
logging.info("parameters %s" % parameters)
with gin.unlock_config():
gin.parse_config(
['%s=%s' % (k, v) for k, v in parameters.items()])
train_eval(root_dir)
device_queue.put(device)
except Exception as e:
logging.info(e)
raise e
z, kl_loss = encoder.sampling_forward(inputs)
outputs = decoding_layers(z)
loss = tf.reduce_mean(100 * loss_f(inputs - outputs) + kl_loss)
model = tf.keras.Model(inputs, outputs, name="vae")
model.add_loss(loss)
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.1))
model.summary()
x_train = np.random.randn(10000, 1)
x_val = np.random.randn(10000, 1)
x_test = np.random.randn(10, 1)
y_test = model(x_test.astype(np.float32))
hist = model.fit(x_train,
epochs=epochs,
batch_size=batch_size,
validation_data=(x_val, None))
y_test = model(x_test.astype(np.float32))
reconstruction_loss = float(tf.reduce_mean(loss_f(x_test - y_test)))
print("reconstruction_loss:", reconstruction_loss)
self.assertLess(reconstruction_loss, 0.05)
if __name__ == '__main__':
from alf.utils.common import set_per_process_memory_growth
set_per_process_memory_growth()
tf.test.main()
