1 files changed, 47 insertions, 0 deletions
diff --git a/cli/app/commands/process/random.py b/cli/app/commands/process/random.py
new file mode 100644
index 0000000..77551aa
--- /dev/null
+++ b/cli/app/commands/process/random.py
@@ -0,0 +1,47 @@
+import click
+
+from app.utils import click_utils
+from app.settings import app_cfg
+
+from os.path import join
+import time
+
+from PIL import Image
+
+@click.command('')
+# @click.option('-i', '--input', 'opt_dir_in', required=True, 
+#   help='Path to input image glob directory')
+# @click.option('-r', '--recursive', 'opt_recursive', is_flag=True)
+@click.pass_context
+def cli(ctx):
+  """
+  """
+  module = hub.Module('https://tfhub.dev/deepmind/bigbigan-resnet50/1')
+
+  # Sample a batch of 8 random latent vectors (z) from the Gaussian prior. Then
+  # call the generator on the latent samples to generate a batch of images with
+  # shape [8, 128, 128, 3] and range [-1, 1].
+  z = tf.random.normal([8, 120])  # latent samples
+  gen_samples = module(z, signature='generate', as_dict=True)['upsampled']
+
+  for sample in gen_samples:
+    img = Image.fromarray(sample, "RGB")
+    fp_img_out = int(time.time() * 1000) + '.png'
+    img.save(join(app_cfg.DIR_OUTPUTS, fp_img_out))
+  # # Given a batch of 256x256 RGB images in range [-1, 1], call the encoder to
+  # # compute predicted latents z and other features (e.g. for use in downstream
+  # # recognition tasks).
+  # images = tf.placeholder(tf.float32, shape=[None, 256, 256, 3])
+  # features = module(images, signature='encode', as_dict=True)
+
+  # # Get the predicted latent sample `z_sample` from the dict of features.
+  # # Other available features include `avepool_feat` and `bn_crelu_feat`, used in
+  # # the representation learning results.
+  # z_sample = features['z_sample']  # shape [?, 120]
+
+  # # Compute reconstructions of the input `images` by passing the encoder's output
+  # # `z_sample` back through the generator. Note that raw generator outputs are
+  # # half the resolution of encoder inputs (128x128). To get upsampled generator
+  # # outputs matching the encoder input resolution (256x256), instead use:
+  # #     recons = module(z_sample, signature='generate', as_dict=True)['upsampled']
+  # recons = module(z_sample, signature='generate')  # shape [?, 128, 128, 3]