即使没有任何物体，Resnet也会显示错误的预测 [英] Resnet is showing wrong predictions even without any object
问题描述
我试图使用resnet在有缺陷的镀层和没有缺陷的板之间进行分类.对于这两个类别，我都有2000个图像的数据集.但是，当我进行实时测试时，即使相机下方没有任何物体(光洁的板或有缺陷的板)，它也显示出变形". 我在下面提供我的培训代码和测试代码.请尝试找出可能是什么问题
I was trying to classify between defected plated and not defected plates using resnet. I have a dataset of 2000 images for each of the two categories. But when I tested it in the real-time it is showing "defected" even though there is no object(either fair or defected plate) under the camera. I am below providing my training code and testing code below. Please try to find out what could be the problem
测试代码:
image =frame
#print(image.shape)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
ret,thresh = cv2.threshold(gray,160,255,0)
contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
height, width, channels = image.shape
min_x, min_y = width, height
max_x = max_y = 0
for cnt in contours:
area = cv2.contourArea(cnt)
if area > 400:
(x, y, w, h) = cv2.boundingRect(cnt)
min_x, max_x = min(x, min_x), max(x + w, max_x)
min_y, max_y = min(y, min_y), max(y + h, max_y)
if (w>200) and (h>200):
roi1 = image[y:y + h, x:x + w]
roi = cv2.resize(roi1, (64, 64))
roi = roi.astype("float") / 255.0
# order channel dimensions (channels-first or channels-last)
# depending on our Keras backend, then add a batch dimension to
# the image
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
# make predictions on the input image
pred = model.predict(roi)
if (pred[0][1]) > .96:
label = "Defect"
color = (0, 0, 255)
confidence = pred[0][1]
elif (pred[0][0]) > .32:
label = "Fair"
color = (0, 255, 0)
confidence = pred[0][0]
#pred = pred.argmax(axis=1)[0]
# label = "Fair" if pred == 0 else "Defected"
# color = (0, 255, 0) if pred == 0 else (0, 0, 255)
cv2.putText(roi1, label, (3, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
color, 2)
cv2.putText(roi1, "confidence:"+str(confidence*100)+"%", (3, 40),
cv2.FONT_HERSHEY_SIMPLEX, 0.5,
(255,255,255), 2)
培训代码:
NUM_EPOCHS = 500
BS = 32
# derive the path to the directories containing the training,
# validation, and testing splits, respectively
TRAIN_PATH = os.path.sep.join([args["dataset"], "training"])
VAL_PATH = os.path.sep.join([args["dataset"], "validation"])
TEST_PATH = os.path.sep.join([args["dataset"], "testing"])
# determine the total number of image paths in training, validation,
# and testing directories
totalTrain = len(list(paths.list_images(TRAIN_PATH)))
totalVal = len(list(paths.list_images(VAL_PATH)))
totalTest = len(list(paths.list_images(TEST_PATH)))
# initialize the training training data augmentation object
trainAug = ImageDataGenerator(
rescale=1 / 255.0,
rotation_range=20,
zoom_range=0.05,
width_shift_range=0.05,
height_shift_range=0.05,
shear_range=0.05,
horizontal_flip=True,
fill_mode="nearest")
# initialize the validation (and testing) data augmentation object
valAug = ImageDataGenerator(rescale=1 / 255.0)
# initialize the training generator
trainGen = trainAug.flow_from_directory(
TRAIN_PATH,
class_mode="categorical",
target_size=(64, 64),
color_mode="rgb",
shuffle=True,
batch_size=32)
# initialize the validation generator
valGen = valAug.flow_from_directory(
VAL_PATH,
class_mode="categorical",
target_size=(64, 64),
color_mode="rgb",
shuffle=False,
batch_size=BS)
# initialize the testing generator
testGen = valAug.flow_from_directory(
TEST_PATH,
class_mode="categorical",
target_size=(64, 64),
color_mode="rgb",
shuffle=False,
batch_size=BS)
# initialize our Keras implementation of ResNet model and compile it
model = ResNet.build(64, 64, 3, 2, (2, 2, 3),
(32, 64, 128, 256), reg=0.0005)
opt = SGD(lr=1e-1, momentum=0.9, decay=1e-1 / NUM_EPOCHS)
model.compile(loss="binary_crossentropy", optimizer=opt,
metrics=["accuracy"])
# train our Keras model
H = model.fit_generator(
trainGen,
steps_per_epoch=totalTrain // BS,
validation_data=valGen,
validation_steps=totalVal // BS,
epochs=NUM_EPOCHS)
# reset the testing generator and then use our trained model to
# make predictions on the data
print("[INFO] evaluating network...")
testGen.reset()
predIdxs = model.predict_generator(testGen,
steps=(totalTest // BS) + 1)
# for each image in the testing set we need to find the index of the
# label with corresponding largest predicted probability
predIdxs = np.argmax(predIdxs, axis=1)
# show a nicely formatted classification report
print(classification_report(testGen.classes, predIdxs,
target_names=testGen.class_indices.keys()))
# save the network to disk
print("[INFO] serializing network to '{}'...".format(args["model"]))
model.save(args["model"])
当我通过视频进行测试时，它显示出对缺陷板的亲和力，公平板的置信度得分非常低，而缺陷板的置信度得分却很高.
When I was testing through video, it was showing an affinity towards the defected plates, confidence score for fair plates were very less and that for defected plates were very high.
推荐答案
此类网络的输出是跨类的概率.除非您这样做，否则不包括虚无"类.如果您在实验室环境中(听起来)，那么您的测试区域的规律性可能允许这样做.即使它们极低，网络也将始终具有 some 个最高得分的输出类别，尽管使用softmax激活，各个类别的总和将始终等于1.在各种情况下都有一些方法可以解决此问题，但是在很大程度上，它被认为是迫切需要积极研究的领域.
The output of such a network is a probability across classes. This does not include a 'nothing' class, unless you make it so. If you're in a lab environment (as it sounds) then perhaps the regularity of your testing area might permit this. The network will always have some highest scoring output class, even if they are all extremely low, although with softmax activation the sum across classes will always equal one. There are some methods for handling this in various scenarios, but largely it's considered an area of urgent active research.
除此之外，您的网络性能无法预测；这就是AI应用程序的整个领域.您需要通过实验进行改进.
Beyond that, the performance of your network is unable to be predicted; that's the entire field of AI application. You'll need to improve it experimentally.
这篇关于即使没有任何物体，Resnet也会显示错误的预测的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
