Created by: SaviorD7

How I can switch dimension of input image data ?

There is my data:

img = fluid.layers.data(name='img', shape=[ 1, 150, 150], dtype='float32')
label = fluid.layers.data(name='label', shape=[1], dtype='int64')

Data format:

{'data': array([[0.07843137, 0.13333333, 0.18039216, ..., 0.30588235, 0.27843137,
        0.25882353],
       [0.07058824, 0.10588235, 0.16862745, ..., 0.29803922, 0.28235294,
        0.25882353],
       [0.0745098 , 0.10980392, 0.16470588, ..., 0.29803922, 0.2745098 ,
        0.25882353],
       ...,
       [0.        , 0.        , 0.        , ..., 0.        , 0.        ,
        0.        ],
       [0.        , 0.        , 0.        , ..., 0.        , 0.        ,
        0.        ],
       [0.        , 0.        , 0.        , ..., 0.        , 0.        ,
        0.        ]]), 'label': array([0])}

Uploading data:

data_path_test = '../data/data52182/chest_xray/test'
uploaded_test_data = xray_dataset.upload_data(data_path_test)

def train_test(train_test_program):
    acc_set = []
    for data in uploaded_test_data:
        acc_np = exe.run(program=train_test_program,
                                feed={'img': np.array([data['data']]), 'label': np.array([data['label']])},
                                fetch_list=["accuracy_0.tmp_0"])

Get this:

InvalidArgumentError: The input of Op(Conv) should be a 4-D or 5-D Tensor. But received: input's dimension is 3, input's shape is [1, 150, 150].
  [Hint: Expected in_dims.size() == 4 || in_dims.size() == 5 == true, but received in_dims.size() == 4 || in_dims.size() == 5:0 != true:1.] at (/paddle/paddle/fluid/operators/conv_op.cc:59)
  [operator < conv2d > error]

How can I reshape image [150x150] into 4-D tensor?