WeSign/spoterembedding
1
0
Fork 0
Code Issues Pull Requests 1 Packages Projects Releases Wiki Activity

Fingerspelling embedding + ClearML

Browse Source
This commit is contained in:
Victor Mylle
2023-05-21 20:30:12 +00:00
parent 2cbf11eb00
commit bd2b848eac
26 changed files with 2465 additions and 176 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
preprocessing/create_google_asl_landmarks_dataset.py
View File

@@ -4,6 +4,8 @@ import pandas as pd
from tqdm.auto import tqdm
import json
from normalization.blazepose_mapping import map_blazepose_df
def create(train_landmark_files, train_csv, dataset_folder, test_size):
os.makedirs(dataset_folder, exist_ok=True)
@@ -17,15 +19,15 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
mapping = {
'pose_0': 'nose',
'pose_1': 'leftEye',
'pose_2': 'rightEye',
'pose_3': 'leftEar',
'pose_4': 'rightEar',
'pose_5': 'leftShoulder',
'pose_6': 'rightShoulder',
'pose_7': 'leftElbow',
'pose_8': 'rightElbow',
'pose_9': 'leftWrist',
'pose_10': 'rightWrist',
'pose_4': 'rightEye',
'pose_7': 'leftEar',
'pose_8': 'rightEar',
'pose_11': 'leftShoulder',
'pose_12': 'rightShoulder',
'pose_13': 'leftElbow',
'pose_14': 'rightElbow',
'pose_15': 'leftWrist',
'pose_16': 'rightWrist',
'left_hand_0': 'wrist_left',
'left_hand_1': 'thumbCMC_left',
@@ -77,7 +79,7 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
columns.append(f'{v}_X')
columns.append(f'{v}_Y')
for _, row in tqdm(train_df.head(6000).iterrows(), total=6000):
for _, row in tqdm(train_df.head(10000).iterrows(), total=10000):
path, participant_id, sequence_id, sign = row['path'], row['participant_id'], row['sequence_id'], row['sign']
parquet_file = os.path.join(train_landmark_files, str(participant_id), f"{sequence_id}.parquet")
@@ -136,6 +138,7 @@ def create(train_landmark_files, train_csv, dataset_folder, test_size):
video_data.append(new_landmark_data)
video_data = pd.concat(video_data, axis=0, ignore_index=True)
video_data = map_blazepose_df(video_data, rename=False)
video_data.to_csv(os.path.join(dataset_folder, 'spoter.csv'), index=False)
train_landmark_files = 'data/train_landmark_files'