ValueError:输入0与层vggface_resnet50不兼容:预期的shape=(None，224,224，3)，发现的shape=(None，1,224,224，3)
ValueError:输入0与层vggface_resnet50不兼容:预期的shape=(None，224,224，3)，发现的shape=(None，1,224,224，3)
提问于 2020-12-20 05:42:48
我想使用https://morioh.com/p/a07857cbc76d中的代码来匹配我的人脸项目的chokepoint数据集中的人脸，我提取了人脸，并希望使用VGGface和余弦来匹配它们，但得到了这个错误，你能帮助我吗？
ValueError:在用户代码中：
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1478 predict_function *
return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1468 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1461 run_step **
outputs = model.predict_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:1434 predict_step
return self(x, training=False)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py:998 __call__
input_spec.assert_input_compatibility(self.input_spec, inputs, self.name)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py:274 assert_input_compatibility
', found shape=' + display_shape(x.shape))
ValueError: Input 0 is incompatible with layer vggface_resnet50: expected shape=(None, 224, 224, 3), found shape=(None, 1, 224, 224, 3)下面是提取人脸的代码：
def extract_face_from_image(image_path, required_size=(224, 224)):
image = plt.imread(image_path)
detector = MTCNN()
faces = detector.detect_faces(image)
face_images = []
for face in faces:
x1, y1, width, height = face['box']
x2, y2 = x1 + width, y1 + height
face_boundary = image[y1:y2, x1:x2]
face_image = Image.fromarray(face_boundary)
face_image = face_image.resize(required_size)
face_array = asarray(face_image)
face_images.append(face_array)
return face_images
extracted_face = extract_face_from_image('/content/301.jpg')
plt.imshow(extracted_face[0])
plt.show()这是匹配人脸的代码：
def get_model_scores(faces):
samples = asarray(faces, 'float32')
samples = preprocess_input(samples, version=2)
model = VGGFace(model='resnet50', include_top=False, input_shape=(224, 224, 3), pooling='avg')
return model.predict(samples)
faces = [extract_face_from_image(image_path) for image_path in ['/content/125.jpg',
'/content/126.jpg']]
model_scores = get_model_scores(faces)
if cosine(model_scores[0], model_scores[1]) <= 0.4:
print("Faces Matched")回答 1
Stack Overflow用户
发布于 2021-07-05 17:26:31
老问题，但将extract_face_from_image更改为：
def extract_face_from_image(image_path, required_size=(224, 224)):
# load image and detect faces
image = plt.imread(image_path)
detector = MTCNN()
faces = detector.detect_faces(image)
# extract the bounding box from the requested face
x1, y1, width, height = faces[0]['box']
x2, y2 = x1 + width, y1 + height
# extract the face
face_boundary = image[y1:y2, x1:x2]
image = cv2.resize(face_boundary, required_size)
return image工作得很好。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/65374755
复制相关文章
相似问题
腾讯云开发者
