ValueError: Filter must not be larger than the input: Filter: (8, 8) Input: (3, 160)

[gpavlov2016]

Hi,

I'm having this issue when running train steering model:

(snakes) guy_pavlov84@instance-1:~/research$ sudo ./train_steering_model.py --port 5557 --val_port 5556
Using TensorFlow backend.
Traceback (most recent call last):
  File "./train_steering_model.py", line 62, in <module>
    model = get_model()
  File "./train_steering_model.py", line 31, in get_model
    model.add(Convolution2D(16, 8, 8, subsample=(4, 4), border_mode="same"))
  File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 308, in add
    output_tensor = layer(self.outputs[0])
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 514, in __call__
    self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 572, in add_inbound_node
    Node.create_node(self, inbound_layers, node_indices, tensor_indices)
  File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 149, in create_node
    output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
  File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 466, in call
    filter_shape=self.W_shape)
  File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 1579, in conv2d
    x = tf.nn.conv2d(x, kernel, strides, padding=padding)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 394, in conv2d
    data_format=data_format, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 704, in apply_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2262, in create_op
    set_shapes_for_outputs(ret)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1702, in set_shapes_for_outputs
    shapes = shape_func(op)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 246, in conv2d_shape
    padding)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 184, in get2d_conv_output_size
    (row_stride, col_stride), padding_type)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.py", line 149, in get_conv_output_size
    "Filter: %r Input: %r" % (filter_size, input_size))
ValueError: Filter must not be larger than the input: Filter: (8, 8) Input: (3, 160)

Any idea what that might be? This is the setup:

(snakes) guy_pavlov84@instance-1:~/research$ pip freeze
funcsigs==1.0.2
h5py==2.6.0
Keras==1.1.0
mock==2.0.0
numpy==1.11.2
pbr==1.10.0
PyYAML==3.12
pyzmq==15.4.0
scipy==0.18.1
six==1.10.0
tensorflow==0.5.0
Theano==0.8.2
zmq==0.0.0

[pprivulet]

Have you solved this problem? I have got the same problem as you.

[gpavlov2016]

Yes, at some point in a new release of keras the order of parameters of input_shape and output_shape was changed. To solve this we need to make two adjustments:

1. input_shape=(ch, row, col) == > input_shape=(row, col, ch) (line 28 in train_steering_model.py) the same for output_shape
2. flip the input data accordingly - add two lines after line 17 and before line 18 in train_steering_model.py: X = numpy.swapaxes(X, 2, 3) X = numpy.swapaxes(X, 3, 4)

[pprivulet]

Hey I solved the problem following your instructions, thank you very much.

[skywong1230]

Hey, I solved the problem following your instructions, then another problem is appear: After I trained the steering model, then use the following command to visualize the results: "./view_steering_model.py ./outputs/steering_model/steering_angle.json"

It got errors: Exception: Error when checking : expected lambda_input_1 to have shape (None, 160, 320, 3) but got array with shape (1, 3, 160, 320)

We need to modify the code in "view_steering_model.py" to slove the problem?

[pprivulet]

Yes, we have to change the code near the line 113 and 114 according to above instructions. Good luck.

[skywong1230]

Yes, thank you! I have changed the code near line 115,

Before: predicted_steers = model.predict(img[None, :, :, :].transpose(0, 3, 1, 2))[0][0]

After: predicted_steers = model.predict(img[None, :, :, :].transpose(0, 1, 2, 3))[0][0]

Than, it works. Thank you.

[cakeinspace]

hey can you tell me what the line from utils import load, save is doing and more importantly how i can install utils

[sunny1986]

@gpavlov2016 Your solution works for me too but ran into another issue.

Using TensorFlow backend. Epoch 1/200 Traceback (most recent call last): File "train_steering_model.py", line 70, in nb_val_samples=1000 File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 895, in fit_generator pickle_safe=pickle_safe) File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1444, in fit_generator 'or (x, y). Found: ' + str(generator_output)) Exception: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None

Any ideas why I might be seeing this?

[sunny1986]

I was able to figure out that I didn't include numpy in my imports in the train_steering_model.py file and hence it was giving me the above error.... However now I am running into the same issue as #27 and my training gets killed even before the 2nd epoch is done. Any ideas or suggestions will be very helpful. FYI - I don't think I have a powerful machine on which I am running this on as this seems to be aresource issue. What are the minimum system requirements for me to have it train successfully?

[pandamax]

same problem occurred

[ahmedyahia3393]

in the view steering model.py file I found his error (ValueError: bad marshal data (unknown type code)) result when trying to execute the view steering model.py here is the result from the cmd prompt

Traceback (most recent call last): File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\utils\generic_utils.py ", line 229, in func_load raw_code = codecs.decode(code.encode('ascii'), 'base64') UnicodeEncodeError: 'ascii' codec can't encode character '\xe0' in position 46: ordinal not in range(128)

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "view_steering_model.py", line 94, in model = model_from_json(json.load(jfile)) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\models.py", line 349, in model_from_json return layer_module.deserialize(config, custom_objects=custom_objects) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\layers_init_.py", l ine 55, in deserialize printable_module_name='layer') File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\utils\generic_utils.py ", line 144, in deserialize_keras_object list(custom_objects.items()))) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\models.py", line 1349, in from_config layer = layer_module.deserialize(conf, custom_objects=custom_objects) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\layers_init_.py", l ine 55, in deserialize printable_module_name='layer') File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\utils\generic_utils.py ", line 144, in deserialize_keras_object list(custom_objects.items()))) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\layers\core.py", line 711, in from_config function = func_load(config['function'], globs=globs) File "C:\Users\lenovo\Anaconda3\lib\site-packages\keras\utils\generic_utils.py ", line 234, in func_load code = marshal.loads(raw_code) ValueError: bad marshal data (unknown type code)