def End_Net_Out(self, X1, pooled_input2, phase_rgb, phase):
"""
Computation Graph
"""
with tf.variable_scope('ResNet34_RGB'):
RGB_Net_obj = model.ResNet34_RGB(X1, phase_rgb)
with tf.device('/device:GPU:0'):
output_rgb, summary1 = RGB_Net_obj.Net()
# output_rgb = tf.reshape(output_rgb, (batch_size * Frame, 6, 20, 512))
with tf.variable_scope('ResNet34_Depth'):
Depth_Net_obj = model.ResNet34_Depth(pooled_input2, phase)
with tf.device('/device:GPU:0'):
output_depth, summary2 = Depth_Net_obj.Net()
# output_depth = tf.reshape(output_depth, [batch_size, Frame, 6, 20, 256])
with tf.variable_scope('End_Net'):
with tf.device('/device:GPU:0'):
cnn_output, summaries = self.End_Net(output_rgb, output_depth,
phase, phase_rgb)
return cnn_output, summaries + summary1 + summary2
import urllib.request
# Download a pre-trained MNIST model for inception score calculation.
# This is a tiny model (<100kb).
if not os.path.exists(MODEL_PATH):
print("downloading model")
os.makedirs(os.path.dirname(MODEL_PATH), exist_ok=True)
urllib.request.urlretrieve(
"https://github.com/ray-project/ray/raw/master/python/ray/tune/"
"examples/pbt_dcgan_mnist/mnist_cnn.pt", MODEL_PATH)
dataloader = get_data_loader()
if not args.smoke_test:
plot_images(dataloader)
# load the pretrained mnist classification model for inception_score
mnist_cnn = Net()
mnist_cnn.load_state_dict(torch.load(MODEL_PATH))
mnist_cnn.eval()
mnist_model_ref = ray.put(mnist_cnn)
# __tune_begin__
scheduler = PopulationBasedTraining(
time_attr="training_iteration",
metric="is_score",
mode="max",
perturbation_interval=5,
hyperparam_mutations={
# distribution for resampling
"netG_lr": lambda: np.random.uniform(1e-2, 1e-5),
"netD_lr": lambda: np.random.uniform(1e-2, 1e-5),
})