def train(poss, negs, modelname):
outsize = 2
net = mlpbase.MLP_PROXY(modelname)
posnum = len(poss)
negnum = len(negs)
samplenum = 2 * np.minimum(posnum, negnum)
featdim = len(poss[0])
samples = np.zeros((samplenum, featdim))
targets = [[0] for k in range(samples.shape[0])]
for k in range(samples.shape[0] / 2):
samples[k, :] = np.array(poss[k])
targets[k][0] = 1
for k in range(samples.shape[0] / 2):
idx = k + samples.shape[0] / 2
samples[idx, :] = np.array(negs[k])
targets[idx][0] = 0
targets = net.target_vec2mat(targets, outsize)
samples, targets = net.shuffle(samples, targets)
net.pre_normalization(samples)
samples = net.normalization(samples)
insize = samples.shape[1]
net.create([insize, np.int64((insize + outsize) / 3), outsize])
print 'train :', samples.shape
net.train(samples, targets, 1000, 0.001)
net.save()
print modelname, ' saved!'
return
def predict_images(indir, posdir, negdir, netname):
net = mlpbase.MLP_PROXY(netname)
net.load()
posnum = 0
negnum = 0
for root, dirs, names in os.walk(indir):
for name in names:
sname, ext = os.path.splitext(name)
ext.lower()
if 0 != cmp(ext, '.jpg') and 0 != cmp(ext, '.jpeg'):
continue
feat = gen_feat(os.path.join(root, name))
label = predictK(np.reshape(np.array(feat), (1, -1)), net)
label = label[0]
if label == 0:
negnum += 1
if negdir != None:
shutil.copy(os.path.join(root, name), negdir)
else:
posnum += 1
if posdir != None:
shutil.copy(os.path.join(root, name), posdir)
if (negnum + posnum) % 1000 == 0:
print 'pos ratio = ', posnum * 1.0 / (negnum + posnum)
print 'finished! pos ratio = ', posnum * 1.0 / (negnum + posnum)
return
def demo(rootdir):
outsize = 4
mlp = mb.MLP_PROXY('ocrmlp.dat')
feats, target_list = load_all_sample(os.path.join(rootdir, 'train'))
samples = np.array(feats)
targets = mlp.target_vec2mat(target_list, outsize)
samples, targets = mlp.shuffle(samples, targets)
insize = samples.shape[1]
mlp.create([insize, 64, outsize])
print 'train ', samples.shape, ',', targets.shape
#normalization
mlp.pre_normalization(samples)
samples = mlp.normalization(samples)
mlp.train(samples, targets, 1000)
mlp.save()
mlp.load()
print 'predict...'
feats, target_list0 = load_all_sample(os.path.join(rootdir, 'test'))
samples = np.array(feats)
#norm
samples = mlp.normalization(samples)
targets = mlp.predict(samples)
target_list1 = mlp.target_mat2vec(targets, outsize, -1)
hit = 0
for a, b in zip(target_list0, target_list1):
if len(a) == len(b) and len(a) == 1 and a[0] == b[0]:
hit += 1
print len(target_list1), ',', hit, ',', hit * 1.0 / len(target_list1)
def load_net_for_predict(netinfo):
nets = []
with open(netinfo, 'r') as f:
for line in f:
line = line.strip()
netname, featid, votew = line.split(',')
net = mlpbase.MLP_PROXY(netname)
net.load()
featid = np.int64(featid)
votew = np.float64(votew)
nets.append([net, featid, votew])
return nets
def predict_slidingwindowK(imgpath, netname, outpath, netsinfo):
nets = []
if netname is not None:
net = mlpbase.MLP_PROXY(netname)
net.load()
nets.append([net, 0, 100])
else:
nets = load_net_for_predict(netsinfo)
img = cv2.imread(imgpath, 1)
img = cv2.cvtColor(img, cv2.COLOR_BGR2YUV)
objs = []
sizelist = []
lastw = 90
for k in range(5):
sizelist.append(np.int64(lastw))
lastw = lastw * 1.2
for objw in sizelist:
objh = np.int64(objw / 3)
if objh < 10:
continue
stepw = objw / 5
steph = objh / 5
if stepw < 5:
stepw = 5
if steph < 5:
steph = 5
for y in range(0, img.shape[0] - objh, steph):
for x in range(0, img.shape[1] - objw, stepw):
subimg = img[y:y + objh, x:x + objw, :]
votescore = 0
for netinfo in nets:
net, fid, votew = netinfo
feat = gen_featK(subimg, fid)
label, score = predictK(
np.reshape(np.array(feat), (1, -1)), net, -2048)[0]
if label != 1:
break
votescore += votew * score
if label != 1:
continue
if votescore > 0.5:
objs.append([x, y, x + objw, y + objh])
if outpath != None:
img = cv2.cvtColor(img, cv2.COLOR_YUV2BGR)
for rect in objs:
x0, y0, x1, y1 = rect
cv2.rectangle(img, (x0, y0), (x1, y1), (255, 0, 0), 2)
cv2.imwrite(outpath, img)
return objs
if len(sys.argv) == 4 and 0 == cmp(sys.argv[1], '-train'):
posdir = sys.argv[2]
negdir = sys.argv[3]
poss = load_feats(posdir)
negs = load_feats(negdir)
train(poss, negs, netpath)
if len(sys.argv) == 3 and 0 == cmp(sys.argv[1], '-prdimg'):
indir = sys.argv[2]
predict_images(indir, None, None, netpath)
if len(sys.argv) == 5 and 0 == cmp(sys.argv[1], '-prdimg'):
indir = sys.argv[2]
posdir = sys.argv[3]
negdir = sys.argv[4]
predict_images(indir, posdir, negdir, netpath)
if len(sys.argv) == 4 and 0 == cmp(sys.argv[1], '-prdsw'):
indir = sys.argv[2]
outdir = sys.argv[3]
predict_slidingwindow(indir, outdir, netpath)
if len(sys.argv) == 5 and 0 == cmp(sys.argv[1], '-prdsw'):
indir = sys.argv[2]
outdir = sys.argv[3]
netsinfo = sys.argv[4]
predict_slidingwindow(indir, outdir, None, netsinfo)
if len(sys.argv) == 4 and 0 == cmp(sys.argv[1], '-cfmt'):
modelpath = sys.argv[2]
outpath = sys.argv[3]
net = mlpbase.MLP_PROXY(modelpath)
net.load()
net.write_in_c_format(outpath)
print outpath, ' saved'