def time_equalize(src_dir, dst_dir, img_width, img_height, new_time_depth):
'''Make image stacks in src_dir have the same number of frames. Place results in dst_dir'''
do_copy = src_dir != dst_dir
for f in os.listdir(src_dir):
ext = os.path.splitext(f)[1].lower()
# copy zip roi files without modification
if ext == '.zip' and do_copy:
shutil.copy(src_dir + f, dst_dir)
# time equalize indvidual videos
elif ext == '.tif' or ext == '.tiff':
data = load_stack(src_dir + f)
resized = zoom(data, (float(new_time_depth) / data.shape[0], 1, 1))
tifffile.imsave(dst_dir + f, resized.squeeze())
def downsample_helper(files_list, img_width, img_height, mean_proj_bins,
max_proj_bins):
'''Mean and max project to covert image files in list to single downsampled numpy array'''
mean_stack = np.zeros((0, img_width, img_height), dtype=np.float32)
full_stack = np.zeros((0, img_width, img_height), dtype=np.float32)
# mean projections
for f in files_list:
full_stack = np.vstack((full_stack, load_stack(f)))
for i in range(0, full_stack.shape[0], mean_proj_bins):
if full_stack.shape[0] - (
i +
mean_proj_bins) < mean_proj_bins and f == files_list[-1]:
m = np.mean(full_stack[i:, :, :], axis=0)
m = np.expand_dims(m, axis=0)
mean_stack = np.vstack((mean_stack, m))
break
elif full_stack.shape[0] - i < mean_proj_bins:
full_stack = full_stack[i:, :, :]
else:
m = np.mean(full_stack[i:i + mean_proj_bins, :, :], axis=0)
m = np.expand_dims(m, axis=0)
mean_stack = np.vstack((mean_stack, m))
# max projections
max_stack = np.zeros((0, img_width, img_height), dtype=np.float32)
for i in range(0, mean_stack.shape[0], max_proj_bins):
if mean_stack.shape[0] - (i + max_proj_bins) < max_proj_bins:
m = np.max(mean_stack[i:, :, :], axis=0)
m = np.expand_dims(m, axis=0)
max_stack = np.vstack((max_stack, m))
break
else:
m = np.max(mean_stack[i:i + max_proj_bins, :, :], axis=0)
m = np.expand_dims(m, axis=0)
max_stack = np.vstack((max_stack, m))
return max_stack
def load_files(self):
'''load a new image and corresponding ROIs'''
current_files = self.files[self.files_keys[self.current_index]]
self.filename_label.config(text=self.files_keys[self.current_index])
self.image = load_stack(current_files[0])
self.image_slider.config(to=self.image.shape[0] - 1)
self.image_slider.set(0)
self.image_index = 0
self.convnet_rois = np.load(current_files[1])['rois']
self.convnet_roi_probs = np.load(current_files[1])['roi_probabilities']
self.indexed_roi_probs = sorted(
[(v, i) for i, v in enumerate(self.convnet_roi_probs)],
reverse=True)
assert (self.convnet_rois.shape[0] == self.convnet_roi_probs.shape[0])
self.roi_slider.config(from_=self.convnet_rois.shape[0])
if self.manual_thresh.get().strip() == "":
self.roi_slider.set(self.convnet_rois.shape[0])
self.roi_index = self.convnet_rois.shape[0]
else:
new_index = self.convnet_rois.shape[0]
for j, (p, ind) in enumerate(self.indexed_roi_probs):
if p < float(self.manual_thresh.get()):
new_index = j
break
self.roi_index = new_index
self.just_set_thresh = True
self.roi_slider.set(new_index)
if current_files[2] is not None:
self.gt_rois = load_rois(current_files[2], self.img_width,
self.img_height)
self.gt_rois = self.gt_rois.max(axis=0)
self.draw_canvas()