Write the values of the predicted bounding boxes in measure_map

[sivaramakrishnan-rajaraman]

I wish to store the values of the predicted bounding boxes 'all_dets' for each test image to a CSV file so that I can use the predicted data for later use. I wish to write the values in the format 'img_name, x1, x2, y1, y2, key'. Could somebody help me how to do it?

for key in bboxes:
		bbox = np.array(bboxes[key])

		new_boxes, new_probs = roi_helpers.non_max_suppression_fast(bbox, np.array(probs[key]), overlap_thresh=0.3) #0.5 before gives the best map
		for jk in range(new_boxes.shape[0]):
			(x1, y1, x2, y2) = new_boxes[jk, :]
			det = {'x1': x1, 'x2': x2, 'y1': y1, 'y2': y2, 'class': key, 'prob': new_probs[jk]}
			all_dets.append(det)
print('Elapsed time = {}'.format(time.time() - st))
	t, p = get_map(all_dets, img_data['bboxes'], (fx, fy))