def run_images(self, images, cutoff=0.05):
"""
Run the neural net on a batch of input images.
Inputs:
images: batch of pictures as a [b, X, Y, C] numpy array.
values between 0 and 255 (uint8 range)
cutoff: value to clip boxes at.
Returns:
Array of BoundingBox objects representing the found boxes.
"""
k = p.ANCHOR_COUNT
gs = p.GRID_SIZE
batch_size = 1
start_time = time.time()
activations, deltas, gammas, classes, chosen_anchor = \
self.sess.run(self.all_out,
feed_dict={self.inp_batch: images}) # ,
# self.do: 1.0})
print('Took %f seconds!' % (time.time() - start_time))
gammas = np.reshape(gammas, [-1, gs**2 * k])
chosen_anchor = np.reshape(chosen_anchor, [-1, gs**2])
deltas = np.reshape(deltas, [-1, gs**2 * k, 4])
classes = np.reshape(classes, [-1, gs**2 * k, p.OUT_CLASSES])
class_numbers = np.argmax(classes, axis=2)
box_list = []
anchors = u.create_anchors(gs)
for ib in range(batch_size):
boxes = u.delta_to_box(deltas[ib], anchors)
nms_indices = tf.image.non_max_suppression(u.trans_boxes(boxes),
gammas[ib],
5,
iou_threshold=0.0) \
.eval(session=self.sess)
selected_boxes = boxes[nms_indices]
selected_gamma = gammas[ib, nms_indices]
selected_class = class_numbers[ib, nms_indices]
selected_class_scores = classes[ib, nms_indices]
for i, box in enumerate(selected_boxes):
sm_scores = u.softmax(selected_class_scores[i])
conf = selected_gamma[i] * sm_scores[selected_class[i]]
if conf > cutoff:
print(conf)
box_list.append(
BoundingBox(u.trans_boxes(box), conf,
selected_class[i]))
return box_list
k = p.ANCHOR_COUNT
gs = p.GRID_SIZE
#print(gammas)
gammas = np.reshape(gammas, [-1, gs**2*k])
chosen_anchor = np.reshape(chosen_anchor,[-1,gs**2])
deltas = np.reshape(deltas, [-1, gs**2*k,4])
anchors = u.create_anchors(gs)
classes = np.reshape(classes, [-1,gs**2*k, p.OUT_CLASSES])
class_numbers = np.argmax(classes, axis=2)
for ib in range(batch_size):
#pic = Image.fromarray(img[ib])
max_gamma= 0
for idx in range(gs**2):
#print(np.shape(gammas))
ca = chosen_anchor[ib, idx]
#print( idx+chosen_anchor[ib, idx])
#print(chosen_anchor.shape)
if(gammas[ib,idx*k+ca] > 0.05):
print('Anchor %i chosen at idx = %i for class %i with conf: %f'\
%(ca,idx,class_numbers[ib,idx*k+ca], gammas[ib,idx*k+ca]))
box = u.delta_to_box(deltas[ib,ca+idx*k,:],
anchors[ca+idx*k])
print(u.trans_boxes(box))
if(gammas[ib,idx*k+ca] > max_gamma):
max_gamma = gammas[ib,idx*k+ca]
print('BEST')