maestrojeong / deformable_convnet Goto Github PK

Hello, if I set the input image as [1, None, None, 3] instead of [-1,28,28,1], there will come out to the following bugs:

offset_map = tf.reshape(offset_map, [batch, i_h, i_w, f_h, f_w, 2])
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [1, None, None, 5, 5, 2]. Consider casting elements to a supported type.

Do you have any advice? Looking to your reply.

Hello, when i run execute 'python main.py', this program shows
ValueError: Cannot feed value of shape (10000, 784) for Tensor u'Placeholder:0', which has shape '(100, 784)'
in "main.py", line 76, in train
this error is cased by config.py