Loading the data using this code below takes time. Is that normal? Or is there something I'm doing wrong? My google colab session also crashed while running the code. Any help would be appreciated! Thanks!

n_obs = 5

X = np.empty((0, 2 * (n_obs-1)))

y = np.empty((0, 1))

field_ids = np.empty((0, 1))

for tile_id in tile_ids_train:

if tile_id != '1951': # avoid using this specific tile for the Hackathon as it might have a missing file

tile_df = competition_train_df[competition_train_df['tile_id']==tile_id]

label_src = rasterio.open(tile_df[tile_df['asset']=='labels']['file_path'].values[0])

label_array = label_src.read(1)

y = np.append(y, label_array.flatten())

field_id_src = rasterio.open(tile_df[tile_df['asset']=='field_ids']['file_path'].values[0])

field_id_array = field_id_src.read(1)

field_ids = np.append(field_ids, field_id_array.flatten())

tile_date_times = tile_df[tile_df['satellite_platform']=='s1']['datetime'].unique()

X_tile = np.empty((256 * 256, 0))

for date_time in tile_date_times[ : 4 * n_obs : n_obs]:

vv_src = rasterio.open(tile_df[(tile_df['datetime']==date_time) & (tile_df['asset']=='VV')]['file_path'].values[0])

vv_array = np.expand_dims(vv_src.read(1).flatten(), axis=1)

vh_src = rasterio.open(tile_df[(tile_df['datetime']==date_time) & (tile_df['asset']=='VH')]['file_path'].values[0])

vh_array = np.expand_dims(vh_src.read(1).flatten(), axis=1)

X_tile = np.append(X_tile, vv_array, axis = 1)

X_tile = np.append(X_tile, vh_array, axis = 1)

X = np.append(X, X_tile, axis=0)