{
  "id": 51859,
  "title": "ValueError",
  "url": "/competitions/data-science-bowl-2018/discussion/51859",
  "author_name": "William Green",
  "post_date": "2018-03-13T18:15:49.724000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Can someone explain the ValueError below? </p>\n\n<p>ValueError: number of input channels does not match corresponding dimension of filter, 1 != 3</p>\n\n<p>I am trying to build a GAN and keep running into this error message. </p>\n\n<pre><code>ValueError                                Traceback (most recent call last)\n &lt;ipython-input-11-8b297200ba81&gt; in &lt;module&gt;()\n 12 mask = Input((img_height, img_width, seg_ch))\n 13 \n  ---&gt; 14 fake_mask=generator(mask)\n 15 fake_pair=Concatenate(axis=3)([nuclei, fake_mask])\n 16 \n  /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n  __call__(self, inputs, **kwargs)\n617 \n618             # Actually call the layer, collecting output(s), mask(s), and shape(s).\n--&gt; 619             output = self.call(inputs, **kwargs)\n620             output_mask = self.compute_mask(inputs, previous_mask)\n621\n\n/opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n call(self, inputs, mask)\n 2083             return self._output_tensor_cache[cache_key]\n 2084         else:\n -&gt; 2085             output_tensors, _, _ = self.run_internal_graph(inputs, masks)\n 2086             return output_tensors\n 2087 \n\n /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n run_internal_graph(self, inputs, masks)\n 2233                                 if 'mask' not in kwargs:\n 2234                                     kwargs['mask'] = computed_mask\n -&gt; 2235                             output_tensors = _to_list(layer.call(computed_tensor, **kwargs))\n 2236                             output_masks = layer.compute_mask(computed_tensor,\n 2237                                                               computed_mask)\n\n /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/layers/convolutional.py in \n call(self, inputs)\n 166                 padding=self.padding,\n 167                 data_format=self.data_format,\n --&gt; 168                 dilation_rate=self.dilation_rate)\n 169         if self.rank == 3:\n 170             outputs = K.conv3d(\n\n/opt/conda/lib/python3.6/site-packages/Keras-2.1.5-\npy3.6.egg/keras/backend/tensorflow_backend.py in conv2d(x, kernel, strides, padding, \ndata_format, dilation_rate)\n3333         strides=strides,\n3334         padding=padding,\n-&gt; 3335         data_format=tf_data_format)\n3336 \n3337     if data_format == 'channels_first' and tf_data_format == 'NHWC':\n\n/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in convolution(input, \nfilter, padding, strides, dilation_rate, name, data_format)\n779         dilation_rate=dilation_rate,\n780         name=name,\n--&gt; 781         data_format=data_format)\n782     return op(input, filter)\n783 \n\n/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in __init__(self, \ninput_shape, filter_shape, padding, strides, dilation_rate, name, data_format)\n839           \"number of input channels does not match corresponding dimension of \"\n840           \"filter, {} != {}\".format(input_channels_dim,\n--&gt; 841                                     filter_shape[num_spatial_dims]))\n842 \n843     strides, dilation_rate = _get_strides_and_dilation_rate(\n\n ValueError: number of input channels does not match corresponding dimension of filter, 1 != 3\n</code></pre>",
  "messages": [
    {
      "id": 295499,
      "postDate": "2018-03-13T18:15:49.723Z",
      "content": "<p>Can someone explain the ValueError below? </p>\n\n<p>ValueError: number of input channels does not match corresponding dimension of filter, 1 != 3</p>\n\n<p>I am trying to build a GAN and keep running into this error message. </p>\n\n<pre><code>ValueError                                Traceback (most recent call last)\n &lt;ipython-input-11-8b297200ba81&gt; in &lt;module&gt;()\n 12 mask = Input((img_height, img_width, seg_ch))\n 13 \n  ---&gt; 14 fake_mask=generator(mask)\n 15 fake_pair=Concatenate(axis=3)([nuclei, fake_mask])\n 16 \n  /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n  __call__(self, inputs, **kwargs)\n617 \n618             # Actually call the layer, collecting output(s), mask(s), and shape(s).\n--&gt; 619             output = self.call(inputs, **kwargs)\n620             output_mask = self.compute_mask(inputs, previous_mask)\n621\n\n/opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n call(self, inputs, mask)\n 2083             return self._output_tensor_cache[cache_key]\n 2084         else:\n -&gt; 2085             output_tensors, _, _ = self.run_internal_graph(inputs, masks)\n 2086             return output_tensors\n 2087 \n\n /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/engine/topology.py in \n run_internal_graph(self, inputs, masks)\n 2233                                 if 'mask' not in kwargs:\n 2234                                     kwargs['mask'] = computed_mask\n -&gt; 2235                             output_tensors = _to_list(layer.call(computed_tensor, **kwargs))\n 2236                             output_masks = layer.compute_mask(computed_tensor,\n 2237                                                               computed_mask)\n\n /opt/conda/lib/python3.6/site-packages/Keras-2.1.5-py3.6.egg/keras/layers/convolutional.py in \n call(self, inputs)\n 166                 padding=self.padding,\n 167                 data_format=self.data_format,\n --&gt; 168                 dilation_rate=self.dilation_rate)\n 169         if self.rank == 3:\n 170             outputs = K.conv3d(\n\n/opt/conda/lib/python3.6/site-packages/Keras-2.1.5-\npy3.6.egg/keras/backend/tensorflow_backend.py in conv2d(x, kernel, strides, padding, \ndata_format, dilation_rate)\n3333         strides=strides,\n3334         padding=padding,\n-&gt; 3335         data_format=tf_data_format)\n3336 \n3337     if data_format == 'channels_first' and tf_data_format == 'NHWC':\n\n/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in convolution(input, \nfilter, padding, strides, dilation_rate, name, data_format)\n779         dilation_rate=dilation_rate,\n780         name=name,\n--&gt; 781         data_format=data_format)\n782     return op(input, filter)\n783 \n\n/opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in __init__(self, \ninput_shape, filter_shape, padding, strides, dilation_rate, name, data_format)\n839           \"number of input channels does not match corresponding dimension of \"\n840           \"filter, {} != {}\".format(input_channels_dim,\n--&gt; 841                                     filter_shape[num_spatial_dims]))\n842 \n843     strides, dilation_rate = _get_strides_and_dilation_rate(\n\n ValueError: number of input channels does not match corresponding dimension of filter, 1 != 3\n</code></pre>",
      "rawMarkdown": "Can someone explain the ValueError below? \n\nValueError: number of input channels does not match corresponding dimension of filter, 1 != 3\n\nI am trying to build a GAN and keep running into this error message. \n\n    ValueError                                Traceback (most recent call last)\n     "
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "295499": "Can someone explain the ValueError below? \n\nValueError: number of input channels does not match corresponding dimension of filter, 1 != 3\n\nI am trying to build a GAN and keep running into this error message. \n\n    ValueError                                Traceback (most recent call last)\n     "
  }
}