我已经用图像训练了一个模型。现在想将fc-6
特征提取到.npy
文件中。我caffe.set_mode_gpu()
用来运行 caffe.Classifier
和提取特征。
而不是每帧提取和保存特征。我将文件夹的所有功能保存到临时变量中,并将完整视频的结果保存到 npy 文件中(减少对磁盘的写入操作次数)。
我还听说我可以使用 Caffe.Net,然后传递一批图像。但我不确定必须做哪些预处理,如果这更快?
import os
import shutil
import sys
import glob
from multiprocessing import Pool
import numpy as np
import os, sys, getopt
import time
def keep_fldrs(path,listr):
ll =list()
for x in listr:
if os.path.isdir(path+x):
ll.append(x)
return ll
def keep_img(path,listr):
ll = list()
for x in listr:
if os.path.isfile(path+str(x)) & str(x).endswith('.jpg'):
ll.append(x)
return ll
def ifdir(path):
if not os.path.isdir(path):
os.makedirs(path)
# Main path to your caffe installation
caffe_root = '/home/anilil/projects/lstm/lisa-caffe-public/python'
# Model prototxt file
model_prototxt = '/home/anilil/projects/caffe2tensorflow/deploy_singleFrame.prototxt'
# Model caffemodel file
model_trained = '/home/anilil/projects/caffe2tensorflow/snapshots_singleFrame_flow_v2_iter_55000.caffemodel'
sys.path.insert(0, caffe_root)
import caffe
caffe.set_mode_gpu()
net = caffe.Classifier(model_prototxt, model_trained,
mean=np.array([128, 128, 128]),
channel_swap=(2,1,0),
raw_scale=255,
image_dims=(255, 255))
Root='/media/anilil/Data/Datasets/UCf_scales/ori_mv_vis/Ori_MV/'
Out_fldr='/media/anilil/Data/Datasets/UCf_scales/ori_mv_vis/feat_fc6/'
allcalsses=keep_fldrs(Root,os.listdir(Root))
for classin in allcalsses:
temp_class=Root+classin+'/'
temp_out_class=Out_fldr+classin+'/'
ifdir(temp_out_class)
allvids_folders=keep_fldrs(temp_class,os.listdir(temp_class))
for each_vid_fldr in allvids_folders:
temp_pres_dir=temp_class+each_vid_fldr+'/'
temp_out_pres_dir=temp_out_class+each_vid_fldr+'/'
ifdir(temp_out_pres_dir)
all_images=keep_img(temp_pres_dir,os.listdir(temp_pres_dir))
frameno=0
if os.path.isfile(temp_out_pres_dir+'video.npy'):
continue
start = time.time()
temp_npy= np.ndarray((len(all_images),4096),dtype=np.float32)
for each_image in all_images:
input_image = caffe.io.load_image(temp_pres_dir+each_image)
prediction = net.predict([input_image],oversample=False)
temp_npy[frameno,:]=net.blobs['fc6'].data[0]
frameno=frameno+1
np.save(temp_out_pres_dir+'video.npy',temp_npy)
end = time.time()
print "lenght of imgs {} and time taken is {}".format(len(all_images),(end - start))
print ('Class {} done'.format(classin))
输出
lenght of imgs 426 and time taken is 388.539139032
lenght of imgs 203 and time taken is 185.467905998