python - Tensorflow，Keras : Expected to see 1 array(s), 但得到了以下 2 个数组的列表

Question

我对 Tensorflow 和 Keras 很陌生。我正在尝试遵循本教程“https://www.pyimagesearch.com/2020/05/04/covid-19-face-mask-detector-with-opencv-keras-tensorflow-and-deep-learning/”。当框架中只有一张脸时，此代码可以完美运行，但是当我尝试在多个脸上检测 mask 时，它会给我这个错误。这里可能是什么问题？

Traceback (most recent call last):
  File "detect_mask_video.py", line 118, in <module>
(locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)
  File "detect_mask_video.py", line 73, in detect_and_predict_mask
    preds = maskNet.predict(faces)
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", 
line 909, in predict
    use_multiprocessing=use_multiprocessing)
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 462, in predict
steps=steps, callbacks=callbacks, **kwargs)
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 396, in _model_iteration
distribution_strategy=strategy)
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 594, in _process_inputs
steps=steps)
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2472, in _standardize_user_data
exception_prefix='input')
  File "C:\Users\Ravi\anaconda3\lib\site-packages\tensorflow_core\python\keras\engine\training_utils.py", line 531, in standardize_input_data
str(len(data)) + ' arrays: ' + str(data)[:200] + '...')
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 2 arrays: [array([[[[-0.58431375, -0.52156866, -0.32549018],
     [-0.58431375, -0.52156866, -0.32549018],
     [-0.58431375, -0.52156866, -0.3333333 ],
     ...,
     [-0.654902  , -0.7254902 ,...

代码是:

# USAGE
# python detect_mask_video.py 
# import the necessary packages
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from imutils.video import VideoStream
import numpy as np
import argparse
import imutils
import time
import cv2
from pypylon import pylon
import os

def detect_and_predict_mask(frame, faceNet, maskNet):
    # grab the dimensions of the frame and then construct a blob
    # from it

    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300),
        (104.0, 177.0, 123.0))

    # pass the blob through the network and obtain the face detections
    faceNet.setInput(blob)
    detections = faceNet.forward()

    # initialize our list of faces, their corresponding locations,
    # and the list of predictions from our face mask network
    faces = []
    locs = []
    preds = []

    # loop over the detections
    for i in range(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the detection
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the confidence is
        # greater than the minimum confidence
        if confidence > args["confidence"]:
             # compute the (x, y)-coordinates of the bounding box for
             # the object
        box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
        (startX, startY, endX, endY) = box.astype("int")

        # ensure the bounding boxes fall within the dimensions of
        # the frame
        (startX, startY) = (max(0, startX), max(0, startY))
        (endX, endY) = (min(w - 1, endX), min(h - 1, endY))

        # extract the face ROI, convert it from BGR to RGB channel
        # ordering, resize it to 224x224, and preprocess it
        face = frame[startY:endY, startX:endX]
        face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
        face = cv2.resize(face, (224, 224))
        face = img_to_array(face)
        face = preprocess_input(face)
        face = np.expand_dims(face, axis=0)

        # add the face and bounding boxes to their respective
        # lists
        faces.append(face)
        locs.append((startX, startY, endX, endY))

        # only make a predictions if at least one face was detected
        if len(faces) > 0:
        # for faster inference we'll make batch predictions on *all*
        # faces at the same time rather than one-by-one predictions
        # in the above `for` loop
        preds = maskNet.predict(faces)

       # return a 2-tuple of the face locations and their corresponding
       # locations
       return (locs, preds)

   # construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-f", "--face", type=str,
default="face_detector",
help="path to face detector model directory")
ap.add_argument("-m", "--model", type=str,
default="mask_detector.model",
help="path to trained face mask detector model")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
help="minimum probability to filter weak detections")
args = vars(ap.parse_args())

# load our serialized face detector model from disk
print("[INFO] loading face detector model...")
prototxtPath = os.path.sep.join([args["face"], "deploy.prototxt"])
weightsPath = os.path.sep.join([args["face"],
"res10_300x300_ssd_iter_140000.caffemodel"])
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)

# load the face mask detector model from disk
print("[INFO] loading face mask detector model...")
maskNet = load_model(args["model"])

# initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()
time.sleep(2.0)

# loop over the frames from the video stream
while True:

    # grab the frame from the threaded video stream and resize it
    # to have a maximum width of 400 pixels
    frame = vs.read()

    frame = imutils.resize(frame, width=400)

    # detect faces in the frame and determine if they are wearing a
    # face mask or not
    (locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)

    # loop over the detected face locations and their corresponding
    # locations
    for (box, pred) in zip(locs, preds):
    # unpack the bounding box and predictions
        (startX, startY, endX, endY) = box
        (mask, withoutMask) = pred

    # determine the class label and color we'll use to draw
    # the bounding box and text
        label = "Mask" if mask > withoutMask else "No Mask"
        color = (0, 255, 0) if label == "Mask" else (0, 0, 255)

    # include the probability in the label
        label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)

    # display the label and bounding box rectangle on the output
    # frame
        cv2.putText(frame, label, (startX, startY - 10),
        cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
        cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)

    # show the output frame
    cv2.imshow("Frame", frame)
    key = cv2.waitKey(1) & 0xFF

    # if the `q` key was pressed, break from the loop
    if key == ord("q"):
         break

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()

Answer 1

AFAIK Opencv 使用 numpy 作为输入。所以你给它一个由两个 4 维 numpy 数组组成的 python 数组，形状为 (1,x,x,3)。因为你想给几个图像作为输入，你应该给一个 4 维的 numpy 数组，其中第一个维度是批量大小。 (N_imgs，宽度，高度， channel )