我有 2 种不同的深度学习模型用于缺陷检测。一种是对象检测模型，另一种是语义分割模型。目的是将两者集成到单一的预测算法中。我正在寻找结合这两个模型以预测结果的最佳方法。我主要想以组合形式评估这两个模型并计算平均平均精度（mAP）有什么办法可以做到。我无法评估，因为我在代码的预测部分被卡住了。
def _get_detections(generator, model, unetmodel=None, score_threshold=0.05, max_detections=100, save_path=None):
""" Get the detections from the model using the generator.
The result is a list of lists such that the size is:
all_detections[num_images][num_classes] = detections[num_detections, 4 + num_classes]
# Arguments
generator : The generator used to run images through the model.
model : The model to run on the images.
score_threshold : The score confidence threshold to use.
max_detections : The maximum number of detections to use per image.
save_path : The path to save the images with visualized detections to.
# Returns
A list of lists containing the detections for each image in the generator.
"""
all_detections = [[None for i in range(generator.num_classes()) if generator.has_label(i)] for j in range(generator.size())]
all_inferences = [None for i in range(generator.size())]
for i in progressbar.progressbar(range(generator.size()), prefix='Running network: '):
test_class = generator.load_annotations(i)['test_class']
print("------")
if test_class == 'scratches':
usemodel = unetmodel
print("Using unetmodel")
raw_image = generator.load_image(i)
image, scale = generator.resize_image(raw_image.copy())
image = generator.preprocess_image(image)
if keras.backend.image_data_format() == 'channels_first':
image = image.transpose((2, 0, 1))
# run network
start = time.time()
#print (unetmodel.predict_on_batch(np.expand_dims(image, axis=0))[:3])
#prediction = unetmodel.predict_on_batch(np.expand_dims(image, axis=0))[:3]
boxes, scores, labels = (unetmodel.predict_on_batch(np.expand_dims(image, axis=0))[0,:,:,0] > 0.4).astype(np.uint8)
#boxes, scores, labels = unetmodel.predict_on_batch(np.expand_dims(image, axis=0))[:3]
inference_time = time.time() - start
# correct boxes for image scale
boxes /= scale
# select indices which have a score above the threshold
indices = np.where(scores[0, :] > score_threshold)[0]
# select those scores
scores = scores[0][indices]
# find the order with which to sort the scores
scores_sort = np.argsort(-scores)[:max_detections]
# select detections
image_boxes = boxes[0, indices[scores_sort], :]
image_scores = scores[scores_sort]
image_labels = labels[0, indices[scores_sort]]
image_detections = np.concatenate([image_boxes, np.expand_dims(image_scores, axis=1), np.expand_dims(image_labels, axis=1)], axis=1)
else:
usemodel = model
print("Using retinanetmodel")
raw_image = generator.load_image(i)
image, scale = generator.resize_image(raw_image.copy())
image = generator.preprocess_image(image)
if keras.backend.image_data_format() == 'channels_first':
image = image.transpose((2, 0, 1))
# run network
start = time.time()
boxes, scores, labels = model.predict_on_batch(np.expand_dims(image, axis=0))[:3]
inference_time = time.time() - start
# correct boxes for image scale
boxes /= scale
# select indices which have a score above the threshold
indices = np.where(scores[0, :] > score_threshold)[0]
# select those scores
scores = scores[0][indices]
# find the order with which to sort the scores
scores_sort = np.argsort(-scores)[:max_detections]
# select detections
image_boxes = boxes[0, indices[scores_sort], :]
image_scores = scores[scores_sort]
image_labels = labels[0, indices[scores_sort]]
image_detections = np.concatenate([image_boxes, np.expand_dims(image_scores, axis=1), np.expand_dims(image_labels, axis=1)], axis=1)
if save_path is not None:
draw_annotations(raw_image, generator.load_annotations(i), label_to_name=generator.label_to_name)
draw_detections(raw_image, image_boxes, image_scores, image_labels, label_to_name=generator.label_to_name, score_threshold=score_threshold)
cv2.imwrite(os.path.join(save_path, '{}.png'.format(i)), raw_image)
# copy detections to all_detections
for label in range(generator.num_classes()):
if not generator.has_label(label):
continue
#all_detections[i][label] = np.concatenate([image_detections_unet[image_detections_unet[:, -1] == label, :-1]], [image_detections_rnet[image_detections_rnet[:, -1] == label, :-1]])
all_detections[i][label] = image_detections[image_detections[:, -1] == label, :-1]
#all_inferences[i] = np.concatenate(inference_time1, inference_time2)
all_inferences[i] = inference_time
return all_detections, all_inferences
我做了一些修改。请提出任何更改。当我收到以下错误时。
WARNING:tensorflow:Model was constructed with shape (None, 256, 256, 3) for input Tensor("input_4:0", shape=(None, 256, 256, 3), dtype=float32), but it was called on an input with incompatible shape (1, 800, 800, 3).
Traceback (most recent call last):
File "C:\Users\user\venv1\keras-retinanet\keras_retinanet\bin\evaluate_new.py", line 200, in <module>
main()
File "C:\Users\user\venv1\keras-retinanet\keras_retinanet\bin\evaluate_new.py", line 177, in main
save_path=args.save_path
File "C:\Users\user\venv1\keras-retinanet\keras_retinanet\bin\..\..\keras_retinanet\utils\eval_new1.py", line 219, in evaluate
all_detections, all_inferences = _get_detections(generator, model, unetmodel, score_threshold=score_threshold, max_detections=max_detections, save_path=save_path)
File "C:\Users\user\venv1\keras-retinanet\keras_retinanet\bin\..\..\keras_retinanet\utils\eval_new1.py", line 94, in _get_detections
boxes, scores, labels = (unetmodel.predict_on_batch(np.expand_dims(image, axis=0))[0,:,:,0] > 0.4).astype(np.uint8)
ValueError: too many values to unpack (expected 3)
任何帮助表示赞赏。先感谢您。