def sentence_similarity(targets, predictions, sentence_similarity_model,
**unused_kwargs):
with tf.Session() as session:
session.run(
[tf.global_variables_initializer(),
tf.tables_initializer()])
targets_embeddings = session.run(sentence_similarity_model(targets))
predictions_embeddings = session.run(
sentence_similarity_model(predictions))
sentence_similarity_all = np.einsum('ij,ij->i', targets_embeddings,
predictions_embeddings)
sentence_similarity_avg = sentence_similarity_all.mean()
return {"sentence_similarity": sentence_similarity_avg}
def calculate_fvd_from_inference_result(gen_path,
ref_path='./Evaluation/ref',
num_of_video=16,
video_length=10):
VIDEO_LENGTH = video_length
print('{}'.format(video_length))
base_ref = VideoGenerateDataset(ref_path, min_len=VIDEO_LENGTH)
base_tar = VideoGenerateDataset(gen_path, min_len=VIDEO_LENGTH)
bs = num_of_video
assert bs % 16 == 0
videoloader_ref = torch.utils.data.DataLoader(
base_ref,
batch_size=bs, #len(videodataset),
drop_last=True,
shuffle=False)
videoloader_tar = torch.utils.data.DataLoader(
base_tar,
batch_size=bs, #len(videodataset),
drop_last=True,
shuffle=False)
with tqdm(total=len(videoloader_ref), dynamic_ncols=True) as pbar:
for i, data in enumerate(videoloader_ref):
images_ref = data.numpy()
break
for i, data in enumerate(videoloader_tar):
images_tar = data.numpy()
break
with tf.Graph().as_default():
ref_tf = tf.convert_to_tensor(images_ref, dtype=tf.uint8)
tar_tf = tf.convert_to_tensor(images_tar, dtype=tf.uint8)
first_set_of_videos = ref_tf #14592
second_set_of_videos = tar_tf
result = calculate_fvd(
create_id3_embedding(preprocess(first_set_of_videos, (224, 224)),
bs),
create_id3_embedding(preprocess(second_set_of_videos, (224, 224)),
bs))
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
sess.run(tf.tables_initializer())
return sess.run(result)
