# disp_interval = 5000
# log_interval = 250
pretrained_vgg16 = False
fine_tune = False
rand_seed = 64678
if rand_seed is not None:
np.random.seed(rand_seed)
torch.manual_seed(rand_seed)
torch.cuda.manual_seed(rand_seed)
net = CrowdCounter()
network.weights_normal_init(net, dev=0.01)
if pretrained_vgg16:
vgg16_model = models.vgg16(pretrained=True)
# vgg16_model.cuda()
net.DA_Net.copy_params_from_vgg16(vgg16_model)
net.to(device)
Loss_list = []
for epoch in range(start_epoch, start_epoch + 2):
train_loss = train_DA(epoch)
Loss_list.append(train_loss)
if epoch == 1:
test_DA(epoch)
# 记录train_loss
train_loss_txt = open('train_loss.txt', 'w')
for value in Loss_list:
train_loss_txt.write(str(value))
train_loss_txt.write('\n')
train_loss_txt.close()
f.write('MAE: %0.2f, MSE: %0.2f' % (mae,mse))
f.close()
if __name__ == '__main__':
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = False
# data_path = './data/original/shanghaitech/part_B_final/test_data/images/'
# gt_path = './data/original/shanghaitech/part_B_final/test_data/ground_truth_csv/'
data_path = './data/original/shanghaitech/part_A_final/test_data/images/'
gt_path = './data/original/shanghaitech/part_A_final/test_data/ground_truth_csv/'
model_path = './Shanghai_A_Retrain_eps_1_5/saved_models//MCNN_Shanghai_A.h5'
model = CrowdCounter()
trained_model = os.path.join(model_path)
network.load_net(trained_model, model)
model.to(device)
model.eval()
data_loader = ImageDataLoader(data_path, gt_path, shuffle=False, gt_downsample=True, pre_load=True)
eps_list = [0, 0.25, 0.5, 0.75, 1]
print(model_path)
epoch_robust_bound(data_loader, model, device, epsilon_try=0.25)