Keras negative dimension size Conv2D

Question

I have been playing around with the kernel sizes and channel arrangements for a while with no luck. I am not entirely sure of how to calculate the corrector parameters for the Conv2D layers and I am unsure how much changing these parameters will affect the similarity to the model in the paper.

Any help would be greatly appreciated.

The model that I attempting to build based on the design in the literature

input_shape = (4, 30, 180)
model = Sequential()
model.add(Convolution2D(32, (8, 8), strides=(4,4), activation='relu', input_shape=(4,30,180), data_format='channels_first'))
model.add(Activation('relu'))
model.add(Convolution2D(64, (4, 4), strides=(2, 2)))
model.add(Activation('relu'))
model.add(Convolution2D(64, (3, 3), strides=(1, 1)))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dense(2))
model.add(Activation('linear'))

The error messages that I recieved

Traceback (most recent call last):
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1659, in _create_c_op
    c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 3 from 2 for 'conv2d_3/convolution' (op: 'Conv2D') with input shapes: [?,15,2,64], [3,3,64,64].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "stock_env.py", line 101, in <module>
    model.add(Convolution2D(64, (3, 3), strides=(1, 1)))
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/keras/engine/sequential.py", line 181, in add
    output_tensor = layer(self.outputs[0])
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py", line 457, in __call__
    output = self.call(inputs, **kwargs)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/keras/layers/convolutional.py", line 171, in call
    dilation_rate=self.dilation_rate)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/keras/backend/tensorflow_backend.py", line 3650, in conv2d
    data_format=tf_data_format)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 851, in convolution
    return op(input, filter)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 966, in __call__
    return self.conv_op(inp, filter)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 591, in __call__
    return self.call(inp, filter)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/nn_ops.py", line 208, in __call__
    name=self.name)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 1026, in conv2d
    data_format=data_format, dilations=dilations, name=name)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
    op_def=op_def)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
    return func(*args, **kwargs)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
    op_def=op_def)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1823, in __init__
    control_input_ops)
  File "/Users/zacharyfrederick/opt/anaconda3/lib/python3.7/site-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op
    raise ValueError(str(e))
ValueError: Negative dimension size caused by subtracting 3 from 2 for 'conv2d_3/convolution' (op: 'Conv2D') with input shapes: [?,15,2,64], [3,3,64,64].

Thibault Bacqueyrisses · Answer 1 · 2020-02-12T11:41:09.813

You have this error because your Kernels and strides are too big for your inputs, a common start is to use kernels of shape (3, 3) and strides (1, 1).

Try reading on how a convolution is computed to give you intuition on how to set the correct kernel/stride size : http://cs231n.github.io/convolutional-networks/

Moreover you have an input with channel first, so you setted your first conv with channel first, it's great but you to do this for all your convolutions, because by default keras convolution's will use channel last.

For exemple, this is working :

input_shape = (4, 30, 180)
model = Sequential()
model.add(Conv2D(32, (8, 8), strides=(4, 4), activation='relu', input_shape=(4, 30, 180), data_format='channels_first'))
model.add(Activation('relu'))
model.add(Conv2D(64, (4, 4), strides=(1, 1), data_format='channels_first'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3), strides=(1, 1), data_format='channels_first'))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dense(2))
model.add(Activation('linear'))

score 0 · Answer 2 · answered Feb 12 '20 at 11:48

The other answer is correct in diagnosis: after convolutions your image gets reduced and at some point the kernel becomes bigger than image. Try

1) lowering your kernel sizes or

2) adding , padding='same' to your convolution layer.

use Calculate the Output size in Convolution layer to calculate your outputs sizes.

Keras negative dimension size Conv2D

2 Answers2