分配带有形状[2,2,48,64]的张量时的OOM

Question

from bumpy import asarray
from PIL import Image

def extract_face_from_image(image, required_size=(64, 64)):

    image = imgs[key]
    image = (image * 255).round().astype(np.uint8)
    detector = MTCNN()
    faces = detector.detect_faces(image)

    face_images = []

    for face in faces:
        # extract the bounding box from the requested face
        x1, y1, width, height = face['box']
        x2, y2 = x1 + width, y1 + height

        # extract the face
        face_boundary = image[y1:y2, x1:x2]

        # resize pixels to the model size
        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_faces=[extract_face_from_image(img) for img in x]
 print(extracted_faces.shape)

因此，我一直尝试使用(2000,100,100)对图像阵列应用人脸检测，并且每次运行它时，都会遇到内存不足的错误 我正在使用的系统具有64 GB ram Nvidia tesla K80。我试过的是： 减小图像尺寸，切片5个元素以尝试。