def index():
dataset = MNIST(config.DATA_DIR, train=False)
images = []
for i in range(0, min(int(dataset.data.shape[0]), 300)):
images.append(
(i, image_to_base64(get_pil_image_from_dataset(dataset, i))))
return render_template('index.html', sample_images=images)
def read_img(inputQ):
print('Process to write: %s' % os.getpid())
# 读取一帧图像
cap = cv2.VideoCapture(0)
while (True):
rval, frame = cap.read()
if rval:
# cv2.imshow("test2", frame)
# start_time = time.time()
# 转换为base64 编码
b64_code = image_to_base64(frame)
# 将编码后的图像放入输入队列
inputQ.append(b64_code)
def save_html(dsobjects, nick, colors, tmp_path):
''' Output a series of HTML pages from the title, pictures, and
descriptions '''
htmlcode = ''
if len(dsobjects) == 0:
return None
for i, dsobj in enumerate(dsobjects):
htmlcode += HTML_GLUE['slide'][0] + str(i)
htmlcode += HTML_GLUE['slide'][1] + \
HTML_GLUE['div'][0]
if 'title' in dsobj.metadata:
htmlcode += HTML_GLUE['h1'][0] + \
dsobj.metadata['title'] + \
HTML_GLUE['h1'][1]
pixbuf = None
media_object = False
try:
pixbuf = gtk.gdk.pixbuf_new_from_file_at_size(
dsobj.file_path, 800, 600)
key = 'img2'
except:
pixbuf = get_pixbuf_from_journal(dsobj, 300, 225)
key = 'img'
if pixbuf is not None:
tmp = HTML_GLUE[key][0]
tmp += image_to_base64(pixbuf, tmp_path)
tmp += HTML_GLUE[key][1]
if 'description' in dsobj.metadata:
tmp += '<p class="body">' + dsobj.metadata['description'] + '</p>'
htmlcode += tmp + \
HTML_GLUE['div'][1]
return HTML_GLUE['doctype'] + \
HTML_GLUE['html'][0] + \
HTML_GLUE['head'][0] + \
HTML_GLUE['meta'] + \
HTML_GLUE['title'][0] + \
nick + ' ' + _('Portfolio') + \
HTML_GLUE['title'][1] + \
'<style type="text/css">\n<!--\n-->\nbody {background-color:' + colors[0] + ';}\np.head {font-size: 18pt; font-weight: bold; font-family: "Sans"; }\np.body {font-size: 12pt; font-weight: regular; font-family: "Sans"; }\ndiv.box{width:630px; padding:10px; border:5px; margin:7px; background:' + colors[1] + '}\n</style>\n' +\
HTML_GLUE['head'][1] + \
HTML_GLUE['body'][0] + \
htmlcode + \
HTML_GLUE['body'][1] + \
HTML_GLUE['html'][1]
def test_baidu_face_api():
img = cv2.imread("img/leijinpeng.jpg")
baidu = utils.BaiduAPI()
ret = baidu.get_face_cli().face_search(utils.image_to_base64(img),
"BASE64", "ahojcn")
print(ret)
def predict(self, payload):
# Get image from url
try:
image = url_to_image(payload["image_url"])
except:
image = b64_to_image(payload["image_b64"])
orig = image.copy()
(h, w) = image.shape[:2]
# construct a blob from the image
blob = cv2.dnn.blobFromImage(image, 1.0, (300, 300),
(104.0, 177.0, 123.0))
# pass the blob through the network and obtain the face detections
print("[INFO] computing face detections...")
self.net.setInput(blob)
detections = self.net.forward()
# 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 = image[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)
# pass the face through the model to determine if the face
# has a mask or not
(mask, withoutMask) = self.model.predict(face)[0]
# 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(image, label, (startX, startY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
cv2.rectangle(image, (startX, startY), (endX, endY), color, 2)
return image_to_base64(image)
def inference():
testId = request.args.get('testId', None)
if testId is None:
return "ERROR: Invalid testId Parameter", 400
dataset = MNIST(config.DATA_DIR, train=False)
test_id = int(testId)
if test_id < 0 or test_id >= dataset.data.shape[0]:
return "ERROR: Out of Range testId Parameter", 400
test_img = image_to_base64(get_pil_image_from_dataset(dataset, test_id))
device = torch.device('cpu')
model = MNISTNet()
model.load_state_dict(
torch.load(join(config.MODEL_DIR, 'mnist_cnn.pt'),
map_location=device))
model.eval()
normalized_data = MNIST(config.DATA_DIR,
train=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
]))
with torch.no_grad():
data = normalized_data.data[test_id, :, :]
data = data.type(torch.float32)
data = data.unsqueeze(0).unsqueeze(0)
target = normalized_data.targets[test_id]
data, target = data.to(device), target.to(device)
output = model(data)
pred = output.argmax(
dim=1, keepdim=True) # get the index of the max log-probability
output_val = np.exp(output.numpy()).squeeze()
pred_idx = int(pred.numpy()[0][0])
pred_score = output_val[pred_idx]
gt_label = dataset.classes[int(dataset.test_labels[test_id])]
pred_label = dataset.classes[pred_idx]
fig = Figure(figsize=(10, 10), dpi=100)
canvas = FigureCanvas(fig)
ax = fig.subplots()
x = np.arange(0, 10, 1)
ax.set_xticks(x)
# Set ticks labels for x-axis
ax.set_xticklabels(dataset.classes, rotation='vertical', fontsize=18)
# ax = fig.add_axes([.1, .1, .8, .8])
ax.plot(output_val)
# ax.title('Predictions')
inf_img = figure_to_base64(fig)
return render_template('inference.html',
test_id=test_id,
test_img=test_img,
inf_img=inf_img,
gt_label=gt_label,
pred_label=pred_label)
import cv2
from aip import AipFace
import utils
client = AipFace(utils.BAIDU_AI_APP_ID, utils.BAIDU_AI_API_KEY,
utils.BAIDU_AI_SECRET_KEY)
image_type = "BASE64"
group_id = "ahojcn"
user_id = "fancheng"
options = {"user_info": "范程"}
image = cv2.imread("./img/fancheng.jpg")
image_base64 = utils.image_to_base64(image)
# print(client.addUser(image_base64, image_type, group_id, user_id, options))
import requests, json
# host = f'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={utils.BAIDU_AI_API_KEY}&client_secret={utils.BAIDU_AI_SECRET_KEY}'
# response = requests.get(host)
# if response:
# print(response.json())
access_token = '24.e4265a7b77a8cadbdb194334fa9b5cbf.2592000.1611411456.282335-18145377'
request_url = 'https://aip.baidubce.com/rest/2.0/face/v3/faceset/user/add'
data = {
"image": image_base64,
"image_type": "BASE64",
"group_id": "ahojcn",
"user_id": "fancheng",