From b0e26f87787deacc8e48a1c0edd0ef2a23f55e8a Mon Sep 17 00:00:00 2001
From: Mathieu Beligon <mathieu@feedly.com>
Date: Mon, 9 Mar 2020 20:11:28 -0400
Subject: [PATCH] [common] (tf records) fix: add filename in the record as it
is used by tf for evaluation
---
common/research_common/dataset/tensorflow_record.py | 3 +++
1 file changed, 3 insertions(+)
diff --git a/common/research_common/dataset/tensorflow_record.py b/common/research_common/dataset/tensorflow_record.py
index 0267a12..76ed247 100644
--- a/common/research_common/dataset/tensorflow_record.py
+++ b/common/research_common/dataset/tensorflow_record.py
@@ -32,6 +32,7 @@ class TensorflowRecordFactory:
self.from_datasets([dataset], name=dataset.dataset_name)
def example_from_image_annotation(self, image_annotation: ImageAnnotation) -> tf.train.Example:
+ image_name = image_annotation.image_path.name
encoded_jpg = image_annotation.image_path.read_bytes()
key = hashlib.sha256(encoded_jpg).hexdigest()
@@ -50,6 +51,8 @@ class TensorflowRecordFactory:
return tf.train.Example(
features=tf.train.Features(
feature={
+ "image/filename": bytes_feature(image_name.encode("utf8")),
+ "image/source_id": bytes_feature(image_name.encode("utf8")),
"image/height": int64_feature(height),
"image/width": int64_feature(width),
"image/key/sha256": bytes_feature(key.encode("utf8")),
--
GitLab