def generate_crops_test():
detection_dataset = fish_detection.FishDetectionDataset(is_test=True)
def decode_clip(video_id):
frames = detection_dataset.video_clips[video_id]
print(video_id)
os.makedirs('{}/{}'.format(dataset.RULER_CROPS_DIR_TEST, video_id),
exist_ok=True)
dest_w = 720
dest_h = 360
transform = detection_dataset.transform_for_clip(
video_id, dest_w, dest_h)
for frame in frames:
src_fn = '{}/{}/{}.jpg'.format(IMAGES_DIR_TEST, video_id, frame)
dst_fn = '{}/{}/{}.jpg'.format(dataset.RULER_CROPS_DIR_TEST,
video_id, frame)
if os.path.isfile(dst_fn):
continue
img = scipy.misc.imread(src_fn)
crop = skimage.transform.warp(img,
transform,
mode='edge',
order=3,
output_shape=(dest_h, dest_w))
scipy.misc.imsave(dst_fn, crop)
pool = ThreadPool(processes=8)
pool.map(decode_clip, detection_dataset.video_clips.keys())
def prepare_submission():
orig_submission = pd.read_csv('../input/submission_format_zeros.csv')
key_frames = load_key_frames()
detection_ds = fish_detection.FishDetectionDataset(is_test=True)
print('load detections:')
try:
detections, classifications, fish_numbers = utils.load_data(
'../output/cache_submission_det_csl.pkl')
raise FileNotFoundError # TODO: does not worth to cache
except FileNotFoundError:
detections = {}
for video_id in orig_submission.video_id.unique():
df = pd.read_csv(
'../output/detection_results_test/resnet_53/{}_ssd_detection.csv'
.format(video_id))
df_full = pd.DataFrame({'frame': range(MAX_ROWS)})
detection_res = df_full.merge(df, on='frame', how='left')
detections[video_id] = detection_res['w'].fillna(0.0).as_matrix()
print('load classifications:')
classifications = {}
cls_models = [('inception', 1.0)]
fn_mask = '../output/classification_results_test_combined/{}/{}/{}_categories.csv'
for video_id in orig_submission.video_id.unique():
cls_res = np.zeros((MAX_ROWS, len(CLS_COLS)), dtype=np.float32)
for det_id, det_weight in [('resnet_53', 0.5), ('resnet_62', 0.5)]:
for cls_model_name, cls_model_weight in cls_models:
df = pd.read_csv(
fn_mask.format(det_id, cls_model_name, video_id))
df_full = pd.DataFrame({'frame': range(MAX_ROWS)})
cls_res += df_full.merge(
df, on='frame', how='left').fillna(0.0).as_matrix(
columns=CLS_COLS) * det_weight * cls_model_weight
classifications[video_id] = cls_res
print('load fish numbers:')
fish_numbers = {}
for video_id in orig_submission.video_id.unique():
fish_numbers[video_id] = key_frames_to_frame_numbers(
sorted(key_frames[video_id]), res_size=MAX_ROWS)
utils.save_data([detections, classifications, fish_numbers],
'../output/cache_submission_det_csl.pkl')
print('generate transforms')
transforms = {}
for video_id in orig_submission.video_id.unique():
transforms[video_id] = detection_ds.transform_for_clip(video_id)
orig_submission_array = orig_submission.as_matrix()
for res_row in range(orig_submission_array.shape[0]):
row = orig_submission_array[res_row]
video_id = row[VIDEO_ID_IDX]
frame = row[FRAME_IDX]
if res_row % 1000 == 0:
print(res_row, res_row * 100.0 / orig_submission_array.shape[0])
orig_submission_array[res_row,
FISH_NUMBER_IDX] = fish_numbers[video_id][frame]
w = detections[video_id][frame]
vector_global = transforms[video_id](np.array([[0, 0], [w, 0]]))
length = np.linalg.norm(vector_global[0] - vector_global[1])
orig_submission_array[res_row, LENGTH_IDX] = length
cls = classifications[video_id][frame]
clear_conf = cls[-1]
orig_submission_array[res_row,
SPECIES_START_IDX:] = cls[:len(SPECIES_COLS)] * (
0.5 + 0.5 * clear_conf)
orig_submission_array = combine_group_species(orig_submission_array)
orig_submission[
'fish_number'] = orig_submission_array[:, FISH_NUMBER_IDX].astype(
np.float32)
orig_submission['length'] = orig_submission_array[:, LENGTH_IDX].astype(
np.float32)
for species_idx, species in enumerate(SPECIES_COLS):
orig_submission[species] = orig_submission_array[:, SPECIES_START_IDX +
species_idx].astype(
np.float32)
orig_submission.to_csv('../output/submission30_inception_only.csv',
index=False,
float_format='%.8f')