Initial Commit

normalization/blazepose_mapping.py

@@ -62,23 +62,19 @@ def map_blazepose_keypoint(column):
 
 
 def map_blazepose_df(df):
-    to_drop = []
-    renamings = {}
-    for column in df.columns:
-        mapped_column = map_blazepose_keypoint(column)
-        if mapped_column:
-            renamings[column] = mapped_column
-        else:
-            to_drop.append(column)
-    df = df.rename(columns=renamings)
-
     for index, row in df.iterrows():
 
-        sequence_size = len(row["leftEar_Y"])
         lsx = row["leftShoulder_X"]
         rsx = row["rightShoulder_X"]
         lsy = row["leftShoulder_Y"]
         rsy = row["rightShoulder_Y"]
+        # convert all to list
+        lsx = lsx[1:-1].split(",")
+        rsx = rsx[1:-1].split(",")
+        lsy = lsy[1:-1].split(",")
+        rsy = rsy[1:-1].split(",")
+        sequence_size = len(lsx)
+
         neck_x = []
         neck_y = []
         # Treat each element of the sequence (analyzed frame) individually
@@ -88,5 +84,4 @@ def map_blazepose_df(df):
         df.loc[index, "neck_X"] = str(neck_x)
         df.loc[index, "neck_Y"] = str(neck_y)
 
-    df.drop(columns=to_drop, inplace=True)
     return df

normalization/main.py

@@ -5,23 +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'
+DATASET_PATH = './data/wlasl'
 # Load the dataset
-df = pd.read_csv(os.path.join(DATASET_PATH, "WLASL_test_15fps.csv"), encoding="utf-8")
+df = pd.read_csv(os.path.join(DATASET_PATH, "WLASL100_train.csv"), encoding="utf-8")
+
+print(df.head())
+print(df.columns)
 
 # Retrieve metadata
-video_size_heights = df["video_size_height"].to_list()
-video_size_widths = df["video_size_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_size_height"]
-del df["video_size_width"]
+del df["video_height"]
+del df["video_width"]
 
 # Temporarily remove other relevant metadata
 labels = df["labels"].to_list()
-video_fps = df["video_fps"].to_list()
+video_fps = df["fps"].to_list()
 del df["labels"]
-del df["video_fps"]
+del df["fps"]
+del df["split"]
+del df["video_id"]
+del df["label_name"]
+del df["length"]
 
 # Convert the strings into lists
 
@@ -42,6 +49,6 @@ df, invalid_row_indexes = normalize_body_full(df)
 
 # Return the metadata back to the dataset
 df["labels"] = labels
-df["video_fps"] = video_fps
+df["fps"] = video_fps
 
-df.to_csv(os.path.join(DATASET_PATH, "WLASL_test_15fps_normalized.csv"), encoding="utf-8", index=False)
+df.to_csv(os.path.join(DATASET_PATH, "wlasl_train_norm.csv"), encoding="utf-8", index=False)