output_dir = './output/' model_name = os.path.basename(model_path).split('.')[0] file_results = os.path.join(output_dir,'results_' + model_name + '_.txt') if not os.path.exists(output_dir): os.mkdir(output_dir) output_dir = os.path.join(output_dir, 'density_maps_' + model_name) if not os.path.exists(output_dir): os.mkdir(output_dir) net = CrowdCounter() trained_model = os.path.join(model_path) network.load_net(trained_model, net) net.cuda() net.eval() mae = 0.0 mse = 0.0 #load test data data_loader = ImageDataLoader(data_path, gt_csv_path, shuffle=False, gt_downsample=True, pre_load=True) #load test data gt gt_files = os.listdir(gt_path) gt_files.sort() for i, blob in enumerate(data_loader): im_data = blob['data'] gt_data = blob['gt_density'] density_map = net(im_data, gt_data) density_map = density_map.data.cpu().numpy()
def open_model(model_path): model = CrowdCounter() network.load_net(model_path, model) model.eval() return model