# Store the predictions
for ind in range(num_images_chunk):
if model_name == 'yolo' or model_name == 'tiny-yolo':
boxes_pred = yolo_postprocess_net_out(net_out[ind], priors,
classes,
detection_threshold,
nms_threshold)
else:
priors = pickle.load(open('prior_boxes_ssd300.pkl', 'rb'))
real_num_classes = num_classes - 1 # Background is not included
bbox_util = BBoxUtility(real_num_classes,
priors=priors,
nms_thresh=nms_threshold)
boxes_pred = bbox_util.detection_out(
net_out[ind],
background_label_id=0,
confidence_threshold=detection_threshold)
current_img = images[ind]
if 'yolo' in model_name:
current_img = np.transpose(current_img, (1, 2, 0))
plt.imshow(current_img)
currentAxis = plt.gca()
# Compute number of predictions that match with GT with a minimum of 50% IoU
for b in boxes_pred:
pred_idx = np.argmax(b.probs)
# Do not count as prediction if it is below the detection threshold or in the ignore list
if (b.probs[pred_idx] <
detection_threshold) or (pred_idx in ignore_class):
for i,img_path in enumerate(imfiles):
img = image.load_img(img_path, target_size=(input_shape[0], input_shape[1]))
img = image.img_to_array(img)
img = img / 255.
inputs.append(img.copy())
img_paths.append(img_path)
if len(img_paths)%chunk_size == 0 or i+1 == len(imfiles):
inputs = np.array(inputs)
start_time = time.time()
net_out = model.predict(inputs, batch_size=16, verbose=1)
print ('{} images predicted in {:.5f} seconds. {:.5f} fps').format(len(inputs),time.time() - start_time,(len(inputs)/(time.time() - start_time)))
total_fps = total_fps + len(inputs)/(time.time() - start_time)
# predicted boxes
results = bbox_util.detection_out(net_out)
for i,img_path in enumerate(img_paths):
# load ground truth
boxes_true = []
label_path = img_path.replace('jpg','txt')
gt = np.loadtxt(label_path)
if len(gt.shape) == 1:
gt = gt[np.newaxis,]
for j in range(gt.shape[0]):
bx = BoundBox(len(classes))
bx.probs[int(gt[j,0])] = 1.
box = gt[j,:]
bx.xmin = box[1] - box[3]/2
bx.ymin = box[2] - box[4]/2
bx.xmax = box[1] + box[3]/2
bx.ymax = box[2] + box[4]/2