我的 OpenCV 实时网络摄像头演示没有显示准确的情绪

Question

我使用PyTorch按照一个不完整的情感识别教程开发了一段代码。我有很多错误，但由于这里的其他问题，我纠正了它们。但我只是在这个问题上搞砸了。我正在运行我的代码，然后我的网络摄像头打开，但我看到"；"中性"；情绪一直都在，即使很强硬，我也会表现出不同的情绪。但在控制台上，我看到了其他记录的情绪，比如：

tensor(0, device='cuda:0')
tensor(6, device='cuda:0')
tensor(4, device='cuda:0')
tensor(4, device='cuda:0') 

你知道吗？

这是我的代码：

import cv2 ### pip install opencv-python
##pip install open-cv-contrib-python fullpackage
#from deepface import DeepFace ##pip install deepface
import numpy as np
path = "haarcascade_frontalface_default.xml"
font_scale = 1.5
font = cv2.FONT_HERSHEY_PLAIN
#set the rectangle background to white
rectangle_bgr = (255, 255, 255)
# make a black image
img = np.zeros((500, 500))
#set some text
text = "VİDGA Projesi"
#get the width and height of the text box
(text_width, text_height) = cv2.getTextSize(text, font, fontScale=font_scale, thickness=1)[0]
#set the text start position
text_offset_x = 10
text_offset_y = img.shape[0] - 25
#make the coords of the box with a small padding of two pixels
box_coords = ((text_offset_x, text_offset_y), (text_offset_x + text_width + 2, text_offset_y - text_height -2))
cv2.rectangle(img, box_coords[0], box_coords[1], rectangle_bgr, cv2.FILLED)
cv2.putText(img, text, (text_offset_x, text_offset_y), font, fontScale=font_scale, color= (0,0,0), thickness=1)
cap = cv2.VideoCapture(1)
#Check if the webcam is opened correctly
if not cap.isOpened():
cap = cv2.VideoCapture(0)
if not cap.isOpened():
raise IOError("Cannot open webcam")

while True:
ret, frame = cap.read()
#eye_Cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_eye.xml')
faceCascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

if ret == True:

gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
#print(faceCascade.empty())
faces = faceCascade.detectMultiScale(gray,1.1,4)
for x,y,w,h in faces:
roi_gray = gray[y:y+h, x:x+w]
roi_color = frame[y:y+h, x:x+w]
cv2.rectangle(frame, (x,y), (x+w, y+h), (255, 0, 0), 2)
facess = faceCascade.detectMultiScale(roi_gray)
if len(facess) == 0:
print("Face not detected")
else: 
for(ex,ey,ew,eh) in facess:
face_roi = roi_color[ey: ey+eh, ex: ex+ew] ##cropping the face

graytemp = cv2.cvtColor(face_roi, cv2.COLOR_BGR2GRAY)
final_image = cv2.resize(graytemp, (48,48))
final_image = np.expand_dims(final_image, axis =0) #add third dimension
final_image = np.expand_dims(final_image, axis =0) #add fourth dimension
final_image = final_image/255.0 # normalization
dataa = torch.from_numpy(final_image)
dataa = dataa.type(torch.FloatTensor)
dataa = dataa.to(device)
outputs = net(dataa)
Pred = F.softmax(outputs, dim=1)
Predictions = torch.argmax(Pred)
print(Predictions)

font = cv2.FONT_HERSHEY_SIMPLEX

font_scale = 1.5
font = cv2.FONT_HERSHEY_PLAIN

if ((Predictions)==0):
status = "Angry"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==1):
status = "Disgust"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==2):
status = "Fear"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==3):
status = "Happy"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==4):
status = "Sad"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==5):
status = "Surprised"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))

elif ((Predictions)==6):
status = "Neutral"

x1,y1,w1,h1, = 0,0,175,5
# Draw black background rectangle
cv2.rectangle(frame, (x1, x1), (x1 + w1, y1 + h1), (0,0,0), -1)
# Add text
cv2.putText(frame, status, (x1 + int(w1/10), y1 + int(h1/2)), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0,0,255), 2)

cv2.putText(frame, status, (100,150), font, 3,(0,0,255), 2, cv2.LINE_4)

cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255))


if ret == True:
cv2.imshow('VIDGA Emotion Recognition', frame) 
if cv2.waitKey(2) & 0xFF == ord('q'):
break

cap.release()
cv2.destroyAllWindows

Answer 1

Predictions是一个张量，因此您需要它的值，而不是张量本身。

更改此行：

Predictions = torch.argmax(Pred)

这个：

Predictions = torch.argmax(Pred).item()