def main2():
clfP = joblib.load('svmmodels/test/SVMl_clfP.pkl')
clfA = joblib.load('svmmodels/test/SVMl_clfA.pkl')
Dt, cpt, cat = loadData('Btest')
log('testing...')
test2(clfP, clfA, Dt, cpt, cat)
log('testing plastic')
test(clfP, Dt, cpt)
log('testing animals')
test(clfA, Dt, cat)
def get_model(cls):
classifier = RelatedSearchClassifier()
classifier.model = joblib.load(os.sep.join([settings.RELATED_SEARCH_MODEL_BASE_DIR, cls.model_file]), mmap_mode='r')
mc = get_cache()
classifier.classification_dict = mc.get(classification_dict_cache_key)
classifier.num_features = mc.get(num_features_key)
return classifier
list_of_file_names.append(this_image_file_name)
if os.path.isfile(this_image_file_name):
file_exists[kk] = 1
# Loop over the poselets
for pose_indx in range(num_poselets):
bin_dir = "/home/ely/projects/faces/data/performance/binary/poselet_" + str(pose_indx) + "/"
score_dir = "/home/ely/projects/faces/data/performance/score/poselet_" + str(pose_indx) + "/"
cmd1 = "mkdir " + bin_dir; cmd2 = "mkdir " + score_dir
resp = os.system(cmd1); resp = os.system(cmd2);
cur_clf_file = clf_name_prefix + str(pose_indx) + clf_name_postfix
cur_clf = joblib.load(cur_clf_file)
#cur_clf_in = open(cur_clf_file,'r')
#cur_clf = pickle.load(cur_clf_in)
#cur_clf_in.close()
cur_pose_patch = "/home/ely/projects/faces/data/poselets/seed_patches/seed_"+str(pose_indx)+".png"
patch_img = imread(cur_pose_patch)
patch_height, patch_width = patch_img.shape
# Loop over all of the images.
num_file_success = 0
num_images_to_test = 10
while num_file_success < num_images_to_test:
found_file = 0
while not(found_file):
test_indx = random.choice(range(len(url_list)))
def batchtrain(self, njob=1, phase=None, shared_memory='no', verbose='on'):
"""Batch training which is called for rought training as well as
finetuning.
"""
t0 = time()
nnodes = getattr(self, 'nnodes')
dlen = getattr(self, 'dlen')
dim = getattr(self, 'dim')
mapsize = getattr(self, 'mapsize')
#############################################
# Seting the parameters
initmethod = getattr(self, 'initmethod')
mn = np.min(mapsize)
if mn == 1:
mpd = float(nnodes * 10) / float(dlen)
else:
mpd = float(nnodes) / float(dlen)
ms = max(mapsize[0], mapsize[1])
if mn == 1:
ms = ms / 5.
# Based on somtoolbox, Matlab
# case 'train', sTrain.trainlen = ceil(50 * mpd);
# case 'rough', sTrain.trainlen = ceil(10 * mpd);
# case 'finetune', sTrain.trainlen = ceil(40 * mpd);
if phase == 'rough':
# training length
trainlen = int(np.ceil(10 * mpd))
# radius for updating
if initmethod == 'random':
# trainlen = int(np.ceil(15 * mpd))
radiusin = max(1, np.ceil(ms / 2.))
radiusfin = max(1, radiusin / 8.)
elif initmethod == 'pca':
radiusin = max(1, np.ceil(ms / 8.))
radiusfin = max(1, radiusin / 4.)
elif phase == 'finetune':
# train lening length
trainlen = int(np.ceil(40 * mpd))
# radius for updating
if initmethod == 'random':
# trainlen = int(np.ceil(50 * mpd))
radiusin = max(1, ms / 8.) # from radius fin in rough training
radiusfin = max(1, radiusin / 16.)
elif initmethod == 'pca':
radiusin = max(1, np.ceil(ms / 8.) / 4)
radiusfin = 1 # max(1, ms / 128)
radius = np.linspace(radiusin, radiusfin, trainlen)
##################################################
UD2 = getattr(self, 'UD2')
New_Codebook_V = np.empty((nnodes, dim))
New_Codebook_V = getattr(self, 'codebook')
# print 'data is in shared memory?', shared_memory
if shared_memory == 'yes':
data = getattr(self, 'data')
Data_folder = tempfile.mkdtemp()
data_name = os.path.join(Data_folder, 'data')
dump(data, data_name)
data = load(data_name, mmap_mode='r')
else:
data = getattr(self, 'data')
# X2 is part of euclidean distance (x-y)^2 = x^2 +y^2 - 2xy that we use for
# each data row in bmu finding.
# Since it is a fixed value we can skip it during bmu finding for each data
# point, but later we need it calculate quantification error.
X2 = np.einsum('ij, ij->i', data, data)
if verbose == 'on':
print '%s training...' % phase
print 'radius_ini: {}, radius_final: {}, trainlen: {}'.format(
radiusin, radiusfin, trainlen)
for i in range(trainlen):
# In case of Guassian neighborhood
H = np.exp(-1.0 * UD2 / (2.0 * radius[i]**2)).reshape(nnodes, nnodes)
t1 = time()
bmu = None
bmu = self.para_bmu_find(data, New_Codebook_V, njb=njob)
if verbose == 'on':
print
# Updating the codebook
t2 = time()
New_Codebook_V = self.update_codebook_voronoi(data, bmu, H, radius)
# print 'updating nodes: ', round (time() - t2, 3)
if verbose == 'on':
print "epoch: {} ---> elapsed time: {}, quantization error: {}".format(
i + 1, round(time() - t1, 3), np.mean(np.sqrt(bmu[1] + X2)))
self.codebook = New_Codebook_V
bmu[1] = np.sqrt(bmu[1] + X2)
self.bmu = bmu
rel = '''
import segmenttest2
reload(segmenttest2)
from segmenttest2 import *
'''
CAFFE_ROOT = '../caffe/'
ADATA_FOLDER = '../DATA_AWATER/'
BDATA_FOLDER = '../DATA_BWATER/'
MODEL_FILE = CAFFE_ROOT + 'models/bvlc_reference_caffenet/deploy.prototxt'
PRETRAINED = CAFFE_ROOT + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'
IMGCLASS = [line[:-1] for line in open('imnetclasses.txt')]
CLFP = joblib.load('svmmodels/allprob/clfP.pkl')
CLFA = joblib.load('svmmodels/allprob/clfA.pkl')
caffe.set_mode_cpu()
if not 'NET' in locals():
NET = caffe.Classifier(
MODEL_FILE,
PRETRAINED,
mean=np.load(CAFFE_ROOT +
'python/caffe/imagenet/ilsvrc_2012_mean.npy').mean(
1).mean(1),
channel_swap=(2, 1, 0),
raw_scale=255,
image_dims=(256, 256))
# Loop over the poselets
for pose_indx in range(num_poselets):
bin_dir = "/home/ely/projects/faces/data/performance/binary/poselet_" + str(
pose_indx) + "/"
score_dir = "/home/ely/projects/faces/data/performance/score/poselet_" + str(
pose_indx) + "/"
cmd1 = "mkdir " + bin_dir
cmd2 = "mkdir " + score_dir
resp = os.system(cmd1)
resp = os.system(cmd2)
cur_clf_file = clf_name_prefix + str(pose_indx) + clf_name_postfix
cur_clf = joblib.load(cur_clf_file)
#cur_clf_in = open(cur_clf_file,'r')
#cur_clf = pickle.load(cur_clf_in)
#cur_clf_in.close()
cur_pose_patch = "/home/ely/projects/faces/data/poselets/seed_patches/seed_" + str(
pose_indx) + ".png"
patch_img = imread(cur_pose_patch)
patch_height, patch_width = patch_img.shape
# Loop over all of the images.
num_file_success = 0
num_images_to_test = 10
while num_file_success < num_images_to_test:
found_file = 0
while not (found_file):
from initial import *
import classify as cl
from scikits.learn import svm
from scikits.learn.externals import joblib
#import svmtest as st
rel = """
import adatatest
reload(adatatest)
from adatatest import *
"""
clfP = joblib.load('svmmodels/test/SVMl_clfP.pkl')
clfA = joblib.load('svmmodels/test/SVMl_clfA.pkl')
def through(imagefolder,imagename):
b = cl.through(imagefolder,imagename)
dm = b['fc7'].data.mean(axis=0)
a = clfA.predict([dm])
p = clfP.predict([dm])
return int(a[0]),int(p[0])
def test(num=100):
bg = pg = ag = bf = 0
for image in ADATA_TRAIN[:num]:
a,p = through(ADATA_FOLDER,image)
[num,rest] = image.split('_')
typeR = rest[0:2]
at = int(typeR[0])
pt = int(typeR[1])
print a,at,p,pt
rel = '''
import segmenttest
reload(segmenttest)
from segmenttest import *
'''
CAFFE_ROOT = '../caffe/'
ADATA_FOLDER = '../DATA_AWATER/'
BDATA_FOLDER = '../DATA_BWATER/'
MODEL_FILE = CAFFE_ROOT + 'models/bvlc_reference_caffenet/deploy.prototxt'
PRETRAINED = CAFFE_ROOT + 'models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel'
IMGCLASS = [line[:-1] for line in open('imnetclasses.txt')]
CLFP = joblib.load('svmmodels/linearMixed/clfP.pkl')
CLFA = joblib.load('svmmodels/linearMixed/clfA.pkl')
caffe.set_mode_cpu()
if not 'NET' in locals():
NET = caffe.Classifier(
MODEL_FILE,
PRETRAINED,
mean=np.load(CAFFE_ROOT +
'python/caffe/imagenet/ilsvrc_2012_mean.npy').mean(
1).mean(1),
channel_swap=(2, 1, 0),
raw_scale=255,
image_dims=(256, 256))