1 files changed, 56 insertions, 0 deletions
diff --git a/megapixels/commands/datasets/vecs_to_uuid.py b/megapixels/commands/datasets/vecs_to_uuid.py
new file mode 100644
index 00000000..7bb82083
--- /dev/null
+++ b/megapixels/commands/datasets/vecs_to_uuid.py
@@ -0,0 +1,56 @@
+"""
+Crop images to prepare for training
+"""
+
+import click
+
+from app.settings import types
+from app.utils import click_utils
+from app.settings import app_cfg as cfg
+
+@click.command()
+@click.option('-i', '--input', 'opt_fp_in', required=True,
+  help='Input directory')
+@click.option('-r', '--records', 'opt_fp_records', required=True,
+  help='Input directory')
+@click.option('-o', '--output', 'opt_fp_out', required=True,
+  help='Output JSON')
+@click.option('-f', '--force', 'opt_force', is_flag=True,
+  help='Force overwrite file')
+@click.pass_context
+def cli(ctx, opt_fp_in, opt_fp_records, opt_fp_out,opt_force):
+  """Merges UUID with face vectors"""
+  
+  import sys
+  import os
+  from os.path import join
+  from pathlib import Path
+  
+  from tqdm import tqdm
+  import pandas as pd
+
+  from app.utils import logger_utils, file_utils
+  
+  # -------------------------------------------------
+  # init here
+
+  log = logger_utils.Logger.getLogger()
+
+  df_vecs = pd.read_csv(opt_fp_in)
+  df_records = pd.read_csv(opt_fp_records)
+  nrows = len(df_vecs)
+
+  # face vecs
+  uuid_vecs = {}
+
+  for roi_idx, row in tqdm(df_vecs.iterrows(), total=nrows):
+    # make image path
+    record_id = int(row['id'])
+    uuid = df_records.iloc[record_id]['uuid']
+    vec = row['vec'].split(',')
+    uuid_vecs[uuid] = vec
+
+  # save as JSON
+  file_utils.write_json(uuid_vecs, opt_fp_out)
+
+  
+\ No newline at end of file