def voc_ap(model, cfg):
imdb_name = 'voc_2007_test'
output_dir = 'models/testing/' + cfg['exp_name']
if not os.path.exists(output_dir):
os.makedirs(output_dir)
imdb = VOCDataset(imdb_name, '../data', cfg['batch_size'],
yolo_utils.preprocess_test, processes=4, shuffle=False, dst_size=cfg['inp_size'])
net = Darknet19(cfg)
net_utils.load_net(model, net)
net.cuda()
net.eval()
mAP = eval_net(net, cfg, imdb, max_per_image=300, thresh=0.001, output_dir=output_dir, vis=False)
imdb.close()
return mAP
def test_voc_ap(model):
print(model)
imdb = VOCDataset(imdb_name,
cfg.DATA_DIR,
cfg.batch_size,
yolo_utils.preprocess_test,
processes=4,
shuffle=False,
dst_size=cfg.inp_size)
net = Darknet19()
net_utils.load_net(model, net)
net.cuda()
net.eval()
mAP = test_net(net, imdb, max_per_image, thresh, vis)
imdb.close()
return mAP
image.shape,
cfg,
thresh=0.3,
size_index=size_index)
im2show = yolo_utils.draw_detection(image, bboxes, scores,
cls_inds, cfg)
summary_writer.add_image('predict', im2show, step)
train_loss = 0
bbox_loss, iou_loss, cls_loss = 0., 0., 0.
cnt = 0
t.clear()
size_index = randint(0, len(cfg.multi_scale_inp_size) - 1)
print("image_size {}".format(cfg.multi_scale_inp_size[size_index]))
if step > 0 and (step % imdb.batch_per_epoch == 0):
if imdb.epoch in cfg.lr_decay_epochs:
lr *= cfg.lr_decay
optimizer = torch.optim.SGD(net.parameters(),
lr=lr,
momentum=cfg.momentum,
weight_decay=cfg.weight_decay)
save_name = os.path.join(cfg.train_output_dir,
'{}_{}.h5'.format(cfg.exp_name, imdb.epoch))
net_utils.save_net(save_name, net)
print(('save model: {}'.format(save_name)))
step_cnt = 0
imdb.close()
cfg,
thr=0.1)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show,
(int(1000. * float(im2show.shape[1]) / im2show.shape[0]), 1000)) # noqa
cv2.imshow('test', im2show)
cv2.waitKey(0)
with open(det_file, 'wb') as f:
pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)
print('Evaluating detections')
imdb.evaluate_detections(all_boxes, output_dir)
if __name__ == '__main__':
# data loader
imdb = VOCDataset(imdb_name, cfg.DATA_DIR, cfg.batch_size,
yolo_utils.preprocess_test,
processes=1, shuffle=False, dst_size=cfg.multi_scale_inp_size)
net = Darknet19()
net_utils.load_net(trained_model, net)
net.cuda()
net.eval()
test_net(net, imdb, max_per_image, thresh, vis)
imdb.close()
cfg.DATA_DIR,
cfg.batch_size,
yolo_utils.preprocess_test,
processes=1,
shuffle=False,
dst_size=cfg.multi_scale_inp_size)
print('start_test............................')
save_txt_f = open('test_ap_newmodel.txt', 'a+')
save_txt_f.writelines(['test_new_model', '\n'])
save_txt_f.writelines(
['{}_{}.h5'.format(cfg.exp_name, imdb.epoch), '\n'])
save_txt_f.close()
net.eval()
test_net(net, imdb_test_map, max_per_image=10, thresh=0.5, vis=False)
net.train()
imdb_test_map.close()
# =============================================================================
save_name = os.path.join(cfg.train_output_dir,
'{}_{}.h5'.format(cfg.exp_name, imdb.epoch))
net_utils.save_net(save_name, net)
print(('save model: {}'.format(save_name)))
step_cnt = 0
imdb.close()
# =============================================================================
#imdb_test_map.close()
# =============================================================================
origin_time = max_ctime
print('start_write_and_test')
print('newfile_time', max_ctime)
print('file', file_dict[max_ctime])
test_f = open('test_ap_newmodel.txt', mode='a+')
test_f.writelines(['MODELS', '\n', file_dict[max_ctime], '\n'])
test_f.close()
new_mdoels_path = os.path.join(file_dir, file_dict[max_ctime])
imdb_map_newf = VOCDataset(imdb_name,
cfg.DATA_DIR,
cfg.batch_size,
yolo_utils.preprocess_test,
processes=1,
shuffle=False,
dst_size=cfg.multi_scale_inp_size)
net = Darknet19()
net_utils.load_net(new_mdoels_path, net)
net.cuda()
net.eval()
test_net(net, imdb_map_newf, max_per_image, thresh, vis=False)
print('test_this_models_done.....')
imdb_map_newf.close()
torch.cuda.empty_cache()
gc.collect()
time.sleep(1200)
# print(file_dict[max_ctime]) #打印出最新文件名
# print(max_ctime)