我尝试用本地图像替换训练和验证数据.但是在运行训练代码时,它出现了错误:
ValueError:无法压缩dim [1],预期维度为1,对于'sparse_softmax_cross_entropy_loss/remove_squeezable_dimensions/Squeeze'(op:'Squeeze')输入形状得到3:[100,3].
我不知道如何修复它.模型定义代码中没有可见变量.代码是从TensorFlow教程修改的.图像是jpgs.
这是详细的错误消息:
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_log_step_count_steps': 100, '_is_chief': True, '_model_dir': '/tmp/mnist_convnet_model', '_tf_random_seed': None, '_session_config': None, '_save_checkpoints_secs': 600, '_num_worker_replicas': 1, '_save_checkpoints_steps': None, '_service': None, '_keep_checkpoint_max': 5, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x00000288088D50F0>, '_keep_checkpoint_every_n_hours': 10000, '_task_type': 'worker', '_master': '', '_save_summary_steps': 100, '_num_ps_replicas': 0, '_task_id': 0}
Traceback (most recent call last):
File "C:\Users\ASUS\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 686, in _call_cpp_shape_fn_impl
input_tensors_as_shapes, status)
File "C:\Users\ASUS\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 473, in __exit__
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 3 for …