def get_ground_truth_predictors(self, ground_truth, label_map, im=None):
i = 0 #indexes the anchor boxes
j = 0
total_boxes_per_gt = sum(self.anchor_nums)
num_ground_truth_in_im = ground_truth.shape[0]
inds = np.zeros((num_ground_truth_in_im, total_boxes_per_gt), dtype = np.int)
#n index the the detection maps
for n, anchor in enumerate(self.anchor_nums):
offset = sum(self.num_pred_boxes[:n])
try:
center_cells = (ground_truth[:,[0,1]]) // self.strides[n]
except:
print(ground_truth)
assert False
a = offset + self.anchor_nums[n]*(self.inp_dim//self.strides[n]*center_cells[:,1] + center_cells[:,0])
inds[:,sum(self.anchor_nums[:n])] = a
for x in range(1, self.anchor_nums[n]):
inds[:,sum(self.anchor_nums[:n]) + x] = a + x
i += anchor
j += self.num_pred_boxes[n]
candidate_boxes = label_map[inds][:,:,:4]
candidate_boxes = center_to_corner(candidate_boxes)
ground_truth_boxes = center_to_corner(ground_truth.copy()[np.newaxis]).squeeze(0)[:,:4]
candidate_boxes = candidate_boxes.transpose(0,2,1)
ground_truth_boxes = ground_truth_boxes[:,:,np.newaxis]
candidate_ious = bbox_iou(candidate_boxes, ground_truth_boxes, lib="numpy")
prediction_boxes = np.zeros((num_ground_truth_in_im,1), dtype=np.int)
for i in range(num_ground_truth_in_im):
#get the the row and the column of the highest IoU
max_iou_ind = np.argmax(candidate_ious)
max_iou_row = max_iou_ind // total_boxes_per_gt
max_iou_col = max_iou_ind % total_boxes_per_gt
#get the index (in label map) of the box with maximum IoU
max_iou_box = inds[max_iou_row, max_iou_col]
#assign the bounding box to the appropriate gt
prediction_boxes[max_iou_row] = max_iou_box
#zero out all the IoUs for this box so it can't be reassigned to any other gt
box_mask = (inds != max_iou_ind).reshape(-1,len(self.anchors))
candidate_ious *= box_mask
#zero out all the values of the row representing gt that just got assigned so that it
#doesn't participate in the process again
candidate_ious[max_iou_row] *= 0
return (prediction_boxes)
def get_no_obj_candidates(self, ground_truth, label_map, ground_truth_predictors):
total_boxes_per_gt = sum(self.anchor_nums)
num_ground_truth_in_im = ground_truth.shape[0]
inds = np.zeros((num_ground_truth_in_im, total_boxes_per_gt), dtype = np.int)
inds = np.arange(sum(self.num_pred_boxes)).astype(int)
inds = inds[np.newaxis].repeat(num_ground_truth_in_im, axis = 0)
candidate_boxes = label_map[inds][:,:,:4]
candidate_boxes = center_to_corner(candidate_boxes)
ground_truth_boxes = center_to_corner(ground_truth.copy()[np.newaxis]).squeeze(0)[:,:4]
candidate_boxes = candidate_boxes.transpose(0,2,1)
ground_truth_boxes = ground_truth_boxes[:,:,np.newaxis]
candidate_ious = bbox_iou(candidate_boxes, ground_truth_boxes, lib = "numpy")
candidate_ious[:, ground_truth_predictors] = 1
max_ious_per_box = np.max(candidate_ious, 0)
no_obj_cands = (np.nonzero(max_ious_per_box < 0.5)[0].astype(int))
return no_obj_cands
pd.read_csv(ground_truths_file, header=None, sep=' '))
except pd.errors.EmptyDataError:
continue
ground_truths[:, 1:] = center_to_corner_2d(ground_truths[:, 1:] *
orig_im_dim[0])
# ground_truths[:, 1:] = ground_truths[:, 1:] * orig_im_dim[0]
class_labels = ground_truths[:, 0]
# x1y1x2y2
ground_truths = ground_truths[:, 1:]
num_gts += ground_truths.shape[0]
img = img_tmp.to(device)
output = model(img)
print('output ', output)
output = center_to_corner(output)
output = output.unsqueeze(0).view(-1, bbox_attrs)
# keep = np.unique(np.asarray(nms(output, scores=output[:, 5], overlap=0.3)[0]))
# print('keep ', keep)
# output = output[keep, :]
# print('output ', output)
score_box = output[:, 5]
print('score_box ', score_box)
# inp_dim is model input size, im_dim is actual image size
output = np.asarray(output.squeeze(0))
if output.shape[0] > 0:
# Get x1y1x2y2, mask conf, class conf
