def get_emotion(current_face, gray):
"""
inputs:
current_face: (xmin, ymin, w, h)
gray: grayscale frame
outputs:
emotion: from -1 to 1, 1 being most positive, -1 being most negative
"""
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack([transforms.ToTensor()(crop) for crop in crops])),
])
# crop face from grayscale frame
xmin = current_face[0]
xmax = current_face[0] + current_face[2]
ymin = current_face[1]
ymax = current_face[1] + current_face[3]
face = gray[ymin:ymax,xmin:xmax]
# resize and transform
face = (resize(face, (48,48), mode='symmetric')*255).astype('uint8')
img = face[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2)
img = Image.fromarray(img)
inputs = transform_test(img)
class_names = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']
# set device, load model
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
net = vgg.VGG('VGG19')
checkpoint = torch.load('PrivateTest_model.t7')
net.load_state_dict(checkpoint['net'])
net.to(device)
net.eval()
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
inputs = inputs.to(device)
with torch.no_grad():
inputs = Variable(inputs)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
weights = np.array([-0.4,-0.1,-0.1,0.8,-0.4,0.2])
score = F.softmax(outputs_avg, dim=0)
emotion_score = np.sum(score.cpu().detach().numpy()[:6]**0.5*weights)
return emotion_score
def img_10crop(self,img):
"""
数据增强
将图片在左上角，左下角，右上角，右下角，中心进行切割和并做镜像操作，这样的操作使得数据库扩大了10倍
"""
cut_size = [44, 44] # 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack([transforms.ToTensor()(crop) for crop in crops])),
])
inputs = transform_test(img)
return inputs
def getEmotionScore(imageDirectory, resizeImg):
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
raw_img = io.imread(imageDirectory)
if resizeImg == True:
raw_img = cropND(raw_img, (400, 400))
io.imsave("screenshot.jpg", raw_img)
gray = rgb2gray(raw_img)
gray = resize(gray, (48, 48), mode='symmetric').astype(np.uint8)
img = gray[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2)
img = Image.fromarray(img)
inputs = transform_test(img)
net = VGG('VGG19')
checkpoint = torch.load(
os.path.join('FER2013_VGG19', 'PrivateTest_model.t7'))
net.load_state_dict(checkpoint['net'])
net.cuda()
net.eval()
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
inputs = inputs.cuda()
inputs = Variable(inputs, volatile=True)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
score = F.softmax(outputs_avg)
_, predicted = torch.max(outputs_avg.data, 0)
scoreDict = {}
for i in range(len(class_names)):
scoreDict[class_names[i]] = float(score.data.cpu().numpy()[i])
scoreDict["expression"] = str(class_names[int(predicted.cpu().numpy())])
return scoreDict
def img2mood(raw_img):
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
#raw_img = io.imread('images/1.jpg')
gray = rgb2gray(raw_img)
gray = resize(gray, (48, 48), mode='symmetric').astype(np.uint8)
img = gray[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2)
img = Image.fromarray(img)
inputs = transform_test(img)
class_names = [
'Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral'
]
net = VGG('VGG19')
checkpoint = torch.load(os.path.join('FER2013_VGG19',
'PrivateTest_model.t7'),
map_location='cpu')
net.load_state_dict(checkpoint['net'])
#net.cuda()
net.eval()
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
#inputs = inputs.cuda()
inputs = Variable(inputs, volatile=True)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
score = F.softmax(outputs_avg)
_, predicted = torch.max(outputs_avg.data, 0)
emojis_img = io.imread('images/emojis/%s.png' %
str(class_names[int(predicted.cpu().numpy())]))
print("The Expression is %s" %
str(class_names[int(predicted.cpu().numpy())]))
return int(predicted.cpu().numpy()), emojis_img
'''
def predict_emotion(file_name):
raw_img = io.imread(file_name)
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
gray = rgb2gray(raw_img)
gray = resize(gray, (48, 48), mode='symmetric').astype(np.uint8)
img = gray[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2) #(48,48,3)
img = Image.fromarray(img) #转化成PIL文件
inputs = transform_test(img) #transform
class_names = [
'Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral'
]
net = VGG('VGG19') #加载网络模型
checkpoint = torch.load(os.path.join(
'F:/Study/First_Grade/Winter_Vacation/Real-time-face-recognition-master/Facial-Expression-Recognition.Pytorch-master/FER2013_VGG19',
'PrivateTest_model.t7'),
map_location='cpu')
net.load_state_dict(checkpoint['net'])
# net.cuda()
net.eval()
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
# inputs = inputs.cuda()
inputs = Variable(inputs, volatile=True)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
#使用数据增强后的结果测试效果会更强
score = F.softmax(outputs_avg)
# print(type(score)) #tensor
_, predicted = torch.max(score.data, 0)
return score, predicted
total_epoch = 60 # 60
path = os.path.join(opt.dataset + '_' + opt.model, str(opt.fold))
# Data
print('==> Preparing data..')
transform_train = transforms.Compose([
transforms.RandomCrop(cut_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
# 数据扩增
# 随机切割，扩充数据集，减缓了过拟合的作用
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
trainset = CK(split='Training', fold=opt.fold, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset,
batch_size=opt.bs,
shuffle=True,
num_workers=0)
testset = CK(split='Testing', fold=opt.fold, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset,
batch_size=5,
shuffle=False,
num_workers=0)
def computeResult(data):
try:
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack([transforms.ToTensor()(crop) for crop in crops])),
])
#Uses image data in array to compute the image
raw_img = np.array(data, dtype=np.uint8)
gray = rgb2gray(raw_img)
gray = resize(gray, (48,48), mode='symmetric').astype(np.uint8)
img = gray[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2)
# img = Image.fromarray(img)
img = Image.fromarray(img)
inputs = transform_test(img)
class_names = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']
net = VGG('VGG19')
checkpoint = torch.load(os.path.join('FER2013_VGG19', 'PrivateTest_model.t7'))
net.load_state_dict(checkpoint['net'])
net.cuda()
net.eval()
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
inputs = inputs.cuda()
inputs = Variable(inputs, volatile=True)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
score = F.softmax(outputs_avg)
_, predicted = torch.max(outputs_avg.data, 0)
plt.rcParams['figure.figsize'] = (13.5,5.5)
axes=plt.subplot(1, 3, 1)
plt.imshow(raw_img)
plt.xlabel('Input Image', fontsize=16)
axes.set_xticks([])
axes.set_yticks([])
plt.tight_layout()
plt.subplots_adjust(left=0.05, bottom=0.2, right=0.95, top=0.9, hspace=0.02, wspace=0.3)
plt.subplot(1, 3, 2)
ind = 0.1+0.6*np.arange(len(class_names)) # the x locations for the groups
width = 0.4 # the width of the bars: can also be len(x) sequence
color_list = ['red','orangered','darkorange','limegreen','darkgreen','royalblue','navy']
for i in range(len(class_names)):
plt.bar(ind[i], score.data.cpu().numpy()[i], width, color=color_list[i])
plt.title("Classification results ",fontsize=20)
plt.xlabel(" Expression Category ",fontsize=16)
plt.ylabel(" Classification Score ",fontsize=16)
plt.xticks(ind, class_names, rotation=45, fontsize=14)
axes=plt.subplot(1, 3, 3)
emojis_img = io.imread('./images/emojis/%s.png' % str(class_names[int(predicted.cpu().numpy())]))
plt.imshow(emojis_img)
plt.xlabel('Emoji Expression', fontsize=16)
axes.set_xticks([])
axes.set_yticks([])
plt.tight_layout()
# show emojis
#plt.show()
plt.savefig(os.path.join('./images/results/' + 'results.jpg'))
plt.close()
print("Result:" + "%s" %str(class_names[int(predicted.cpu().numpy())]))
except:
print('Cannot find image')
def show_anim(robot, cnt):
# nonlocal model
# read the image sequence for classification
img_path = config.img_path
img_names = [
os.path.join(img_path, 'face_round{}_cnt{}.jpg'.format(cnt, i))
for i in range(10)
]
face_seq = [io.imread(img) for img in img_names]
anim_prob = np.zeros(len(config.anim_names))
for face in face_seq:
## use the model loaded to predict probabilities
## input one figure and get a one-dim array of size 7
'''
complete here !!!
'''
cut_size = 44
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
raw_img = face
gray = rgb2gray(raw_img)
gray = resize(gray, (48, 48), mode='symmetric').astype(np.uint8)
img = gray[:, :, np.newaxis]
img = np.concatenate((img, img, img), axis=2)
img = Image.fromarray(img)
inputs = transform_test(img)
ncrops, c, h, w = np.shape(inputs)
inputs = inputs.view(-1, c, h, w)
#inputs = inputs.cuda()
inputs = Variable(inputs, volatile=True)
outputs = net(inputs)
outputs_avg = outputs.view(ncrops, -1).mean(0) # avg over crops
score = F.softmax(outputs_avg)
_, predicted = torch.max(outputs_avg.data, 0)
prob = score.data.cpu().numpy()
anim_prob += prob
# e.g.
# anim_prob += model(face)
anim_prob = anim_prob / sum(anim_prob)
anim_name = np.random.choice(config.anim_names, 1, p=anim_prob)[0]
print('Playing Animation: ', anim_name)
print('The Expression is: ',
class_names[anim_prob.tolist().index(max(anim_prob))])
robot.anim.play_animation(anim_name)
import transforms as transforms
from skimage import io
from skimage.transform import resize
from models import *
from Fer_DataLoader import Fer_DataLoader
a= 0
f= Fer_DataLoader()
train_data = f.get_test_data()
total = 0
for inputs,_ in train_data:
cut_size = 44
if total == 200 :
break
transform_test = transforms.Compose([
transforms.TenCrop(48),
transforms.Lambda(lambda crops: torch.stack([transforms.ToTensor()(crop) for crop in crops])),
])
'''
raw_img = io.imread(i)
#gray = rgb2gray(raw_img)
gray = resize(raw_img, (48,48), mode='symmetric').astype(np.uint8)
img = gray
img = Image.fromarray(img)
inputs = transform_test(img)
'''
class_names = ['Angry','disgusted','fearful','happy','neutral','sad','surprised']
# Data
# print('==> Preparing data..')
transform_train = transforms.Compose([
transforms.RandomCrop(cut_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
transform_train_mask = transforms.Compose([
transforms.RandomCrop(cut_size_mask),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
transform_test = transforms.Compose([
transforms.TenCrop(cut_size),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
transform_test_mask = transforms.Compose([
transforms.TenCrop(cut_size_mask),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
# trainset = CK(split='Training', fold=opt.fold, transform=transform_train)
trainset = CK_Mask(split='Training',
fold=opt.fold,
transform=transform_train_mask)
trainloader = torch.utils.data.DataLoader(trainset,
import os
import sys
import torch
import yaml
from PIL import Image
import numpy as np
from classifer_fer.models import *
from utils import get_dataset
sys.path.append(os.path.join(os.getcwd(), 'classifer_fer'))
import transforms as transforms
transform_test = transforms.Compose([
transforms.TenCrop(44),
transforms.Lambda(lambda crops: torch.stack(
[transforms.ToTensor()(crop) for crop in crops])),
])
net = VGG('VGG19')
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
checkpoint = torch.load('classifer_fer/FER2013_VGG19/PrivateTest_model.t7',
map_location=device)
net.load_state_dict(checkpoint['net'])
# net.cuda()
net.eval()
# cfg = yaml.load(open('config_celeba_grey.yaml', 'r'))
