Google colaboratory 是否可以训练此工具/模型以恢复常规三维对象

我刚刚尝试了这个PIFuHD来恢复一个普通棋子（骑士/马）的3d模型。 它创建内容为1的test_rect.txt。 那就跑吧！失败，出现下一个错误：

Resuming from  ./checkpoints/pifuhd.pt
Warning: opt is overwritten.
test data size:  2
initialize network with normal
initialize network with normal
generate mesh (test) ...
  0% 0/2 [00:00<?, ?it/s]/content/pifuhd/lib/data/EvalDataset.py:87: UserWarning: loadtxt: Empty input file: "/content/pifuhd/sample_images/test (1)_rect.txt"
  rects = np.loadtxt(rect_path, dtype=np.int32)
  0% 0/2 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/content/pifuhd/apps/simple_test.py", line 30, in <module>
    reconWrapper(cmd, args.use_rect)
  File "/content/pifuhd/apps/recon.py", line 220, in reconWrapper
    recon(opt, use_rect)
  File "/content/pifuhd/apps/recon.py", line 205, in recon
    test_data = test_dataset[i]
  File "/content/pifuhd/lib/data/EvalDataset.py", line 131, in __getitem__
    return self.get_item(index)
  File "/content/pifuhd/lib/data/EvalDataset.py", line 93, in get_item
    im = crop_image(im, rect)
  File "/content/pifuhd/lib/data/EvalDataset.py", line 17, in crop_image
    x, y, w, h = rect
ValueError: not enough values to unpack (expected 4, got 0)

从./checkpoints/pifuhd.pt恢复
警告：opt被覆盖。
测试数据大小：2
用正常值初始化网络
用正常值初始化网络
生成网格（测试）。。。
0% 0/2 [00:00