Primary competition visual

Radiant Earth Spot the Crop Hackathon by #ZindiWeekendz

Helping South Africa
$300 USD
Challenge completed over 4 years ago
Classification
Earth Observation
81 joined
21 active
Starti
Jul 02, 21
Closei
Jul 04, 21
Reveali
Jul 04, 21
Is it normal?
Notebooks · 3 Jul 2021, 07:02 · 4

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)

Discussion 4 answers

mine didn't work completely. I had to remove the axis=0 part but that took forever to load.

3 Jul 2021, 07:05
Upvotes 0

am afraid am going to spend more time loading the data rather than implementing the solution.

3 Jul 2021, 07:06
Upvotes 0
User avatar
Lone_Wolf
University of ghana

its the data size.. it crashes due to memory issues

3 Jul 2021, 09:45
Upvotes 0
User avatar
DoubleAgent
Carnegie mellon university africa

Probably insufficient RAM. I am not certain the most efficient way to handle this. For now, I load the data in batches and append.

Edit

I also use del to delete variables I believe I would no longer need to free memory.