test_snake.py 'Negative Dimension Size caused by...

[gaara100]

Using TensorFlow backend. Traceback (most recent call last): File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 654, in _call_cpp_shape_fn_impl input_tensors_as_shapes, status) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\contextlib.py", line 66, in exit next(self.gen) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 466, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 3 from 2 for 'Conv2D_1' (op: 'Conv2D') with input shapes: [?,2,8,16], [3,3,16,32].

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "test_snake.py", line 13, in model.add(Convolution2D(32, nb_row=3, nb_col=3, activation='relu')) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\models.py", line 332, in add output_tensor = layer(self.outputs[0]) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\engine\topology.py", line 572, in call self.add_inbound_node(inbound_layers, node_indices, tensor_indices) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\engine\topology.py", line 635, in add_inbound_node Node.create_node(self, inbound_layers, node_indices, tensor_indices) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\engine\topology.py", line 166, in create_node output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0])) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\layers\convolutional.py", line 475, in call filter_shape=self.W_shape) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\keras-1.2.2-py3.5.egg\keras\backend\tensorflow_backend.py", line 2691, in conv2d x = tf.nn.conv2d(x, kernel, strides, padding=padding) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 397, in conv2d data_format=data_format, name=name) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 767, in apply_op op_def=op_def) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\ops.py", line 2632, in create_op set_shapes_for_outputs(ret) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\ops.py", line 1911, in set_shapes_for_outputs shapes = shape_func(op) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\ops.py", line 1861, in call_with_requiring return call_cpp_shape_fn(op, require_shape_fn=True) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 595, in call_cpp_shape_fn require_shape_fn) File "C:\Users\Me\Anaconda3\envs\tf_rl\lib\site-packages\tensorflow\python\framework\common_shapes.py", line 659, in _call_cpp_shape_fn_impl raise ValueError(err.message) ValueError: Negative dimension size caused by subtracting 3 from 2 for 'Conv2D_1' (op: 'Conv2D') with input shapes: [?,2,8,16], [3,3,16,32].

I get the above error when I try to run test_snake.py, with Keras version 1.2.2 and Tensorflow-gpu version 1.3.0

Thoughts?

[RozenAstrayChen]

Hi , I have same problem , I found this to fix it

model.add(Convolution2D(32, (3, 3), activation='relu', input_shape=(1, 28, 28), data_format='channels_first'))

add data_format='channels_first'