4 files changed, 99 insertions, 6 deletions
diff --git a/cli/app/commands/process/fetch.py b/cli/app/commands/process/fetch.py
index a558d94..5b6c102 100644
--- a/cli/app/commands/process/fetch.py
+++ b/cli/app/commands/process/fetch.py
@@ -3,6 +3,9 @@ import click
 from app.utils import click_utils
 from app.settings import app_cfg
 
+from os.path import join
+from subprocess import call
+
 @click.command('')
 # @click.option('-i', '--input', 'opt_dir_in', required=True, 
 #   help='Path to input image glob directory')
@@ -10,11 +13,45 @@ from app.settings import app_cfg
 @click.pass_context
 def cli(ctx):
   """
-  Converts directory of images to BigGAN* vectors
   """
 
-  # ------------------------------------------------
-  # imports
-
   # app_cfg.MODELZOO_CFG
-  pass
+  import gensim
+  
+  # from nltk.corpus import wordnet as wn
+  # synsets = wordnet.synsets("fir_tree")
+  # synonyms = [ lemma.name() for lemma in synsets[0].lemmas() ]
+
+  imagenet = Imagenet()
+
+  sentence = "The quick brown fox jumps over the lazy dog"
+  tokens = gensim.utils.simple_preprocess(sentence)
+
+class Imagenet:
+  def __init__():
+    tokens = {}
+    with open(app_cfg.FP_IMAGENET_WORDS, "r") as fp:
+      for line in fp.readlines():
+        wordnet_id, word_list = line.split('\t')
+        words = [word.trim() for word in word_list.split(',')]
+        for word in words:
+          tokens[word] = wordnet_id
+    self.tokens = tokens
+ 
+  def get_wordnet_ids_for_words(tokens):
+    # for token in tokens:
+      # if token in tokens:
+    pass
+
+  def images_from_wordnet_id(wordnet_id):
+    """
+    Given a Wordnet ID, download images for this class
+    """
+    call([
+      "python",
+      join(app_cfg.DIR_APP, "../ImageNet-Datasets-Downloader/downloader.py"),
+      '-data_root', app_cfg.FP_IMAGENET,
+      '-use_class_list', 'True',
+      '-class_list', wordnet_id,
+      '-images_per_class', app_cfg.IMAGENET_IMAGES_PER_CLASS
+    ])
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]
diff --git a/cli/app/settings/app_cfg.py b/cli/app/settings/app_cfg.py
index fe65458..6f99fd0 100644
--- a/cli/app/settings/app_cfg.py
+++ b/cli/app/settings/app_cfg.py
@@ -26,7 +26,8 @@ CLICK_GROUPS = {
 
 SELF_CWD = os.path.dirname(os.path.realpath(__file__))  # Script CWD
 DIR_APP = str(Path(SELF_CWD).parent.parent.parent)
-
+DIR_IMAGENET = join(DIR_APP, 'data_store/imagenet')
+DIR_OUTPUTS = join(DIR_APP, 'data_store/outputs')
 FP_MODELZOO = join(DIR_APP, 'modelzoo/modelzoo.yaml')
 
 # -----------------------------------------------------------------------------
@@ -35,3 +36,11 @@ FP_MODELZOO = join(DIR_APP, 'modelzoo/modelzoo.yaml')
 
 with open(FP_MODELZOO, 'r') as fp:
   MODELZOO_CFG = yaml.load(fp, Loader=yaml.Loader)
+
+# -----------------------------------------------------------------------------
+# Imagenet
+# -----------------------------------------------------------------------------
+
+IMAGENET_IMAGES_PER_CLASS = 200
+FP_IMAGENET_WORDS = join(DIR_IMAGENET, 'words.txt')
+FP_IMAGENET_CLASSES = join(DIR_IMAGENET, 'classes_in_imagenet.csv')
diff --git a/data_store/outputs/.gitkeep b/data_store/outputs/.gitkeep
new file mode 100644
index 0000000..e69de29
--- /dev/null
+++ b/data_store/outputs/.gitkeep