def get_cropped_test_img(fname,
bbox_pred,
pad=None,
as_grey=False,
return_bbox=False):
img = imread(fname, as_grey=as_grey)
h = img.shape[0]
w = img.shape[1]
bbox_pred = bbox_pred * [w, h, w, h]
bbox_pred = np.round(bbox_pred).astype(int)
l = min(max(bbox_pred[0], 0), w)
t = min(max(bbox_pred[1], 0), h)
r = min(max(l + bbox_pred[2], 0), w)
b = min(max(t + bbox_pred[3], 0), h)
if pad is not None:
l, t, r, b = add_padding_to_bbox(l,
t, (r - l), (b - t),
pad / 100.0,
img.shape[1],
img.shape[0],
format='ltrb')
cropped_img = img[t:b, l:r]
if return_bbox:
return cropped_img, bbox_pred
else:
return cropped_img
def get_cropped_test_img(fname, bbox_pred, pad=None, as_grey=False, return_bbox=False):
img = imread(fname, as_grey=as_grey)
h = img.shape[0]
w = img.shape[1]
bbox_pred = bbox_pred * [w, h, w, h]
bbox_pred = np.round(bbox_pred).astype(int)
l = min(max(bbox_pred[0], 0), w)
t = min(max(bbox_pred[1], 0), h)
r = min(max(l + bbox_pred[2], 0), w)
b = min(max(t + bbox_pred[3], 0), h)
if pad is not None:
l, t, r, b = add_padding_to_bbox(
l, t, (r - l), (b - t), pad / 100.0,
img.shape[1], img.shape[0],
format='ltrb'
)
cropped_img = img[t:b, l:r]
if return_bbox:
return cropped_img, bbox_pred
else:
return cropped_img
X_fp = np.memmap(X_fname, dtype=np.float32, mode='w+', shape=X_shape)
y_fp = np.memmap(y_fname, dtype=np.int32, mode='w+', shape=y_shape)
for i, row in tqdm(df.iterrows(), total=len(df)):
fname = os.path.join('data/imgs/', row['Image'])
whale_id = row['whaleID']
x = int(row['x'])
y = int(row['y'])
w = int(row['width'])
h = int(row['height'])
try:
img = imread(fname, as_grey=args.as_grey)
if args.pad > 0:
x, y, w, h = add_padding_to_bbox(x, y, w, h, args.pad / 100.0,
img.shape[1], img.shape[0])
img = img[y:y + h, x:x + w]
img = resize(img, (args.size, args.size))
if args.as_grey:
img = img.reshape(-1, args.size, args.size)
else:
img = img.transpose(2, 0, 1)
img = img.astype(np.float32)
X_fp[i] = img
y_fp[i] = whale_id
X_fp.flush()
y_fp.flush()
X_fp = np.memmap(X_fname, dtype=np.float32, mode='w+', shape=X_shape)
y_fp = np.memmap(y_fname, dtype=np.int32, mode='w+', shape=y_shape)
for i, row in tqdm(df.iterrows(), total=len(df)):
fname = os.path.join('data/imgs/', row['Image'])
whale_id = row['whaleID']
x = int(row['x'])
y = int(row['y'])
w = int(row['width'])
h = int(row['height'])
try:
img = imread(fname, as_grey=args.as_grey)
if args.pad > 0:
x, y, w, h = add_padding_to_bbox(
x, y, w, h, args.pad / 100.0,
img.shape[1], img.shape[0]
)
img = img[y:y + h, x:x + w]
img = resize(img, (args.size, args.size))
if args.as_grey:
img = img.reshape(-1, args.size, args.size)
else:
img = img.transpose(2, 0, 1)
img = img.astype(np.float32)
X_fp[i] = img
y_fp[i] = whale_id
X_fp.flush()