def cls_im(self, im):
im = im.astype(np.float32, copy=True)
normalized_im = T.normalize(im, mean=self.mean, std=self.std)
scale_im, scale_ratio = T.scale(normalized_im, short_size=self.base_size)
crop_ims = []
if self.crop_type == 'center' or self.crop_type == 'single': # for single crop
crop_ims.append(T.center_crop(scale_im, crop_size=self.crop_size))
elif self.crop_type == 'mirror' or self.crop_type == 'multi': # for 10 crops
crop_ims.extend(T.mirror_crop(scale_im, crop_size=self.crop_size))
else:
crop_ims.append(scale_im)
scores = self.inference(np.asarray(crop_ims, dtype=np.float32), output_layer=self.prob_layer)
return np.sum(scores, axis=0)
def eval_batch():
eval_len = len(SET_DICT)
accuracy = np.zeros(len(args.top_k))
start_time = datetime.datetime.now()
for i in xrange(eval_len - args.skip_num):
im = cv2.imread(SET_DICT[i + args.skip_num]['path'])
im = T.bgr2rgb(im)
scale_im = T.pil_resize(Image.fromarray(im), args.base_size)
normalized_im = T.normalize(np.asarray(scale_im) / 255.0, mean=PIXEL_MEANS, std=PIXEL_STDS)
crop_ims = []
if args.crop_type == 'center': # for single crop
crop_ims.append(T.center_crop(normalized_im, crop_size=args.crop_size))
elif args.crop_type == 'multi': # for 10 crops
crop_ims.extend(T.mirror_crop(normalized_im, crop_size=args.crop_size))
else:
crop_ims.append(normalized_im)
score_vec = np.zeros(args.class_num, dtype=np.float32)
iter_num = int(len(crop_ims) / args.batch_size)
timer_pt1 = datetime.datetime.now()
for j in xrange(iter_num):
input_data = np.asarray(crop_ims, dtype=np.float32)[j * args.batch_size:(j + 1) * args.batch_size]
input_data = input_data.transpose(0, 3, 1, 2)
input_data = torch.autograd.Variable(torch.from_numpy(input_data).cuda(), volatile=True)
outputs = MODEL(input_data)
scores = outputs.data.cpu().numpy()
score_vec += np.sum(scores, axis=0)
score_index = (-score_vec / len(crop_ims)).argsort() - 1
timer_pt2 = datetime.datetime.now()
SET_DICT[i + args.skip_num]['evaluated'] = True
SET_DICT[i + args.skip_num]['score_vec'] = score_vec / len(crop_ims)
print 'Testing image: {}/{} {} {}/{} {}s' \
.format(str(i + 1), str(eval_len - args.skip_num), str(SET_DICT[i + args.skip_num]['path'].split('/')[-1]),
str(score_index[0]), str(SET_DICT[i + args.skip_num]['gt']),
str((timer_pt2 - timer_pt1).microseconds / 1e6 + (timer_pt2 - timer_pt1).seconds)),
for j in xrange(len(args.top_k)):
if SET_DICT[i + args.skip_num]['gt'] in score_index[:args.top_k[j]]:
accuracy[j] += 1
tmp_acc = float(accuracy[j]) / float(i + 1)
if args.top_k[j] == 1:
print '\ttop_' + str(args.top_k[j]) + ':' + str(tmp_acc),
else:
print 'top_' + str(args.top_k[j]) + ':' + str(tmp_acc)
end_time = datetime.datetime.now()
w = open(LOG_PTH, 'w')
s1 = 'Evaluation process ends at: {}. \nTime cost is: {}. '.format(str(end_time), str(end_time - start_time))
s2 = '\nThe model is: {}. \nThe val file is: {}. \n{} images has been tested, crop_type is: {}, base_size is: {}, ' \
'crop_size is: {}.'.format(args.model_weights, args.val_file, str(eval_len - args.skip_num),
args.crop_type, str(args.base_size), str(args.crop_size))
s3 = '\nThe PIXEL_MEANS is: ({}, {}, {}), PIXEL_STDS is : ({}, {}, {}).' \
.format(str(PIXEL_MEANS[0]), str(PIXEL_MEANS[1]), str(PIXEL_MEANS[2]), str(PIXEL_STDS[0]), str(PIXEL_STDS[1]),
str(PIXEL_STDS[2]))
s4 = ''
for i in xrange(len(args.top_k)):
_acc = float(accuracy[i]) / float(eval_len - args.skip_num)
s4 += '\nAccuracy of top_{} is: {}; correct num is {}.'.format(str(args.top_k[i]), str(_acc),
str(int(accuracy[i])))
print s1, s2, s3, s4
w.write(s1 + s2 + s3 + s4)
w.close()
if args.save_score_vec:
w = open(LOG_PTH.replace('.txt', 'scorevec.txt'), 'w')
for i in xrange(eval_len - args.skip_num):
w.write(SET_DICT[i + args.skip_num]['score_vec'])
w.close()
print('DONE!')
def eval_batch():
# shuffle_conv1_channel()
eval_len = len(SET_DICT)
# eval_len = 1000
accuracy = np.zeros(len(args.top_k))
start_time = datetime.datetime.now()
for i in xrange(eval_len - args.skip_num):
im = cv2.imread(SET_DICT[i + args.skip_num]['path'])
if (PIXEL_MEANS == np.array([103.52, 116.28, 123.675])).all() and \
(PIXEL_STDS == np.array([57.375, 57.12, 58.395])).all():
scale_im = T.pil_scale(Image.fromarray(im), args.base_size)
scale_im = np.asarray(scale_im)
else:
scale_im, _ = T.scale(im, short_size=args.base_size)
input_im = T.normalize(scale_im, mean=PIXEL_MEANS, std=PIXEL_STDS)
crop_ims = []
if args.crop_type == 'center': # for single crop
crop_ims.append(T.center_crop(input_im, crop_size=args.crop_size))
elif args.crop_type == 'multi': # for 10 crops
crop_ims.extend(T.mirror_crop(input_im, crop_size=args.crop_size))
else:
crop_ims.append(input_im)
score_vec = np.zeros(args.class_num, dtype=np.float32)
iter_num = int(len(crop_ims) / args.batch_size)
timer_pt1 = datetime.datetime.now()
for j in xrange(iter_num):
scores = CLS.inference(
np.asarray(crop_ims, dtype=np.float32)[j * args.batch_size:(j + 1) * args.batch_size],
output_layer=args.prob_layer
)
score_vec += np.sum(scores, axis=0)
score_index = (-score_vec / len(crop_ims)).argsort()
timer_pt2 = datetime.datetime.now()
SET_DICT[i + args.skip_num]['evaluated'] = True
SET_DICT[i + args.skip_num]['score_vec'] = score_vec / len(crop_ims)
print 'Testing image: {}/{} {} {}/{} {}s' \
.format(str(i + 1), str(eval_len - args.skip_num), str(SET_DICT[i + args.skip_num]['path'].split('/')[-1]),
str(score_index[0]), str(SET_DICT[i + args.skip_num]['gt']),
str((timer_pt2 - timer_pt1).microseconds / 1e6 + (timer_pt2 - timer_pt1).seconds)),
for j in xrange(len(args.top_k)):
if SET_DICT[i + args.skip_num]['gt'] in score_index[:args.top_k[j]]:
accuracy[j] += 1
tmp_acc = float(accuracy[j]) / float(i + 1)
if args.top_k[j] == 1:
print '\ttop_' + str(args.top_k[j]) + ':' + str(tmp_acc),
else:
print 'top_' + str(args.top_k[j]) + ':' + str(tmp_acc)
end_time = datetime.datetime.now()
w = open(LOG_PTH, 'w')
s1 = 'Evaluation process ends at: {}. \nTime cost is: {}. '.format(str(end_time), str(end_time - start_time))
s2 = '\nThe model is: {}. \nThe val file is: {}. \n{} images has been tested, crop_type is: {}, base_size is: {}, ' \
'crop_size is: {}.'.format(args.model_weights, args.val_file, str(eval_len - args.skip_num),
args.crop_type, str(args.base_size), str(args.crop_size))
s3 = '\nThe PIXEL_MEANS is: ({}, {}, {}), PIXEL_STDS is : ({}, {}, {}).' \
.format(str(PIXEL_MEANS[0]), str(PIXEL_MEANS[1]), str(PIXEL_MEANS[2]), str(PIXEL_STDS[0]), str(PIXEL_STDS[1]),
str(PIXEL_STDS[2]))
s4 = ''
for i in xrange(len(args.top_k)):
_acc = float(accuracy[i]) / float(eval_len - args.skip_num)
s4 += '\nAccuracy of top_{} is: {}; correct num is {}.'.format(str(args.top_k[i]), str(_acc),
str(int(accuracy[i])))
print s1, s2, s3, s4
w.write(s1 + s2 + s3 + s4)
w.close()
if args.save_score_vec:
w = open(LOG_PTH.replace('.txt', 'scorevec.txt'), 'w')
for i in xrange(eval_len - args.skip_num):
w.write(SET_DICT[i + args.skip_num]['score_vec'])
w.close()
print('DONE!')