print(
"Counting histogram..., config=%s, distance=%s, depth=%s" %
(sample_cache, d_type, depth))
samples = []
data = db.get_data()
for d in data.itertuples():
d_img, d_cls = getattr(d, "img"), getattr(d, "cls")
d_hist = self.gabor_histogram(d_img,
type=h_type,
n_slice=n_slice)
samples.append({'img': d_img, 'cls': d_cls, 'hist': d_hist})
cPickle.dump(
samples, open(os.path.join(cache_dir, sample_cache), "wb",
True))
return samples
if __name__ == "__main__":
db = Database()
# evaluate database
APs = evaluate_class(db, f_class=Gabor, d_type=d_type, depth=depth)
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))
data = db.get_data()
for d in data.itertuples():
d_img, d_cls = getattr(d, "img"), getattr(d, "cls")
d_hist = self.histogram(d_img, type=h_type, n_bin=n_bin, n_slice=n_slice)
samples.append({
'img': d_img,
'cls': d_cls,
'hist': d_hist
})
cPickle.dump(samples, open(os.path.join(cache_dir, sample_cache), "wb", True))
return samples
if __name__ == "__main__":
db = Database()
data = db.get_data()
color = Color()
# test normalize
hist = color.histogram(data.ix[0, 0], type='global')
assert hist.sum() - 1 < 1e-9, "normalize false"
# test histogram bins
def sigmoid(z):
a = 1.0 / (1.0 + np.exp(-1. * z))
return a
np.random.seed(0)
inputs = torch.autograd.Variable(
torch.from_numpy(img).float())
d_hist = vgg_model(inputs)[pick_layer]
d_hist = np.sum(d_hist.data.cpu().numpy(), axis=0)
d_hist /= np.sum(d_hist) # normalize
samples.append({
'img': d_img,
'cls': d_cls,
'hist': d_hist
})
except BaseException:
pass
cPickle.dump(
samples, open(os.path.join(cache_dir, sample_cache), "wb",
True))
return samples
if __name__ == "__main__":
# evaluate database
DB = Database()
APs = evaluate_class(DB, f_class=VGGNetFeat, d_type=d_type, depth=depth)
cls_MAPs = []
for cls, cls_APs in APs.items():
MAP = np.mean(cls_APs)
print("Class {}, MAP {}".format(cls, MAP))
cls_MAPs.append(MAP)
print("MMAP", np.mean(cls_MAPs))