ValueError：“concat”模式只能合并具有匹配输出形状的层，concat轴除外

Question

我正在尝试使用https://github.com/ternaus/kaggle_dstl_submission对LAS数据（无人机数据）进行分类、识别（位置）和分割，比如建筑物、树木和道路。当我运行建筑预测代码（python make_prediction_cropped_buildings.py）时，我面临以下问题：

Using TensorFlow backend.

architecture_128_50_buildings_3_.json

Traceback (most recent call last):
  File "make_prediction_cropped_buildings.py", line 26, in <module>
    model = read_model()
  File "make_prediction_cropped_buildings.py", line 21, in read_model
    model = model_from_json(open(os.path.join('../src/cache', json_name)).read())
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/models.py", line 214, in model_from_json
    return layer_from_config(config, custom_objects=custom_objects)
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/utils/layer_utils.py", line 44, in layer_from_config
    custom_objects=custom_objects)
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 2597, in from_config
    process_layer(layer_data)
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 2593, in process_layer
    layer(input_tensors)
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 1470, in __call__
    node_indices, tensor_indices)
  File "/home/darshan/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 1380, in _arguments_validation
    'Layer shapes: %s' % (input_shapes))

ValueError: "concat" mode can only merge layers with matching output shapes except for the concat axis. Layer shapes: [(None, 1024, 14, 7), (None, 256, 14, 14)]