computer vision - How to speed up caffe classifer in python -

i using python use caffe classifier. got image camera , peform predict image training set. work problem speed slow. thinks 4 frames/second. suggest me way improve computational time in code? problem can explained following. have reload network model age_net.caffemodel size 80mb following code

age_net_pretrained='./age_net.caffemodel' age_net_model_file='./deploy_age.prototxt' age_net = caffe.classifier(age_net_model_file, age_net_pretrained,            mean=mean,            channel_swap=(2,1,0),            raw_scale=255,            image_dims=(256, 256)) 

and each input image (caffe_input), call predict function

prediction = age_net.predict([caffe_input]) 

i think due size of network large. predict function takes long time predict image. think slow time it.
full reference code. changed me.

from conv_net import *  import matplotlib.pyplot plt import numpy np import cv2 import glob import os caffe_root = './caffe'  import sys sys.path.insert(0, caffe_root + 'python') import caffe data_path = './face/' cnn_params = './params/gender_5x5_5_5x5_10.param' face_params = './params/haarcascade_frontalface_alt.xml' def format_frame(frame):     img = frame.astype(np.float32)/255.     img = img[...,::-1]     return img     if __name__ == '__main__':         files = glob.glob(os.path.join(data_path, '*.*'))      # configuration of full convolutional part of cnn     # `d` list of dicts, each dict represents convolution-maxpooling     # layer.      # eg c1 - first layer, convolution window size     # p1 - first layer pooling window size     # f_in1 - first layer no. of input feature arrays     # f_out1 - first layer no. of output feature arrays     d = [{'c1':(5,5),           'p1':(2,2),           'f_in1':1, 'f_out1':5},          {'c2':(5,5),           'p2':(2,2),           'f_in2':5, 'f_out2':10}]      # configuration of mlp part of cnn     # first tuple has fan_in , fan_out of input layer     # of mlp , on.     nnet =  [(800,256),(256,2)]         c = convnet(d,nnet, (45,45))     c.load_params(cnn_params)             face_cascade = cv2.cascadeclassifier(face_params)     cap = cv2.videocapture(0)     cv2.namedwindow("image", cv2.window_normal)      plt.rcparams['figure.figsize'] = (10, 10)     plt.rcparams['image.interpolation'] = 'nearest'     plt.rcparams['image.cmap'] = 'gray'     mean_filename='./mean.binaryproto'     proto_data = open(mean_filename, "rb").read()     = caffe.io.caffe_pb2.blobproto.fromstring(proto_data)     mean  = caffe.io.blobproto_to_array(a)[0]     age_net_pretrained='./age_net.caffemodel'     age_net_model_file='./deploy_age.prototxt'     age_net = caffe.classifier(age_net_model_file, age_net_pretrained,                mean=mean,                channel_swap=(2,1,0),                raw_scale=255,                image_dims=(256, 256))     age_list=['(0, 2)','(4, 6)','(8, 12)','(15, 20)','(25, 32)','(38, 43)','(48, 53)','(60, 100)']     while(true):          val, image = cap.read()                 if image none:             break         image = cv2.resize(image, (320,240))         gray = cv2.cvtcolor(image, cv2.color_bgr2gray)         faces = face_cascade.detectmultiscale(gray, 1.3, 5, minsize=(30,30))          f in faces:             x,y,w,h = f             cv2.rectangle(image, (x,y), (x+w,y+h), (0,255,255))                         face_image_rgb = image[y:y+h, x:x+w]             caffe_input = cv2.resize(face_image_rgb, (256, 256)).astype(np.float32)             prediction = age_net.predict([caffe_input])              print 'predicted age:', age_list[prediction[0].argmax()]                cv2.imshow('image', image)         ch = 0xff & cv2.waitkey(1)         if ch == 27:             break         #break 

try calling age_net.predict([caffe_input]) oversmaple=false:

prediction = age_net.predict([caffe_input], oversample=false) 

the default behavior of predict create 10, different, crops of input image , feed them network classify, disabling option should x10 speedup.