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

30
normalization/main.py
View File

@@ -5,30 +5,30 @@ import pandas as pd
from normalization.hand_normalization import normalize_hands_full
from normalization.body_normalization import normalize_body_full
DATASET_PATH = './data/wlasl'
DATASET_PATH = './data/processed'
# Load the dataset
df = pd.read_csv(os.path.join(DATASET_PATH, "WLASL100_train.csv"), encoding="utf-8")
df = pd.read_csv(os.path.join(DATASET_PATH, "spoter_train.csv"), encoding="utf-8")
print(df.head())
print(df.columns)
# Retrieve metadata
video_size_heights = df["video_height"].to_list()
video_size_widths = df["video_width"].to_list()
# video_size_heights = df["video_height"].to_list()
# video_size_widths = df["video_width"].to_list()
# Delete redundant (non-related) properties
del df["video_height"]
del df["video_width"]
# del df["video_height"]
# del df["video_width"]
# Temporarily remove other relevant metadata
labels = df["labels"].to_list()
video_fps = df["fps"].to_list()
signs = df["sign"].to_list()
del df["labels"]
del df["fps"]
del df["split"]
del df["video_id"]
del df["label_name"]
del df["length"]
del df["sign"]
del df["path"]
del df["participant_id"]
del df["sequence_id"]
# Convert the strings into lists
@@ -41,7 +41,7 @@ for column in df.columns:
# Perform the normalizations
df = normalize_hands_full(df)
df, invalid_row_indexes = normalize_body_full(df)
# df, invalid_row_indexes = normalize_body_full(df)
# Clear lists of items from deleted rows
# labels = [t for i, t in enumerate(labels) if i not in invalid_row_indexes]
@@ -49,6 +49,6 @@ df, invalid_row_indexes = normalize_body_full(df)
# Return the metadata back to the dataset
df["labels"] = labels
df["fps"] = video_fps
df["sign"] = signs
df.to_csv(os.path.join(DATASET_PATH, "wlasl_train_norm.csv"), encoding="utf-8", index=False)
df.to_csv(os.path.join(DATASET_PATH, "spoter_train_norm.csv"), encoding="utf-8", index=False)