Dimension 1 in both shapes must be equal, but are 12 and 24 for 'merge_1/concat' about retina-unet HOT 4 OPEN

Hi, I met the same error.
Then, I changed my keras.json to

"image_data_format" : "channels_first",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"

It worked!

May it help!

from retina-unet.

Have you fixed it ? I have the same problem and seem the solution above not work.
........................................................
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your InputLayer call to the Keras 2 API: InputLayer(dtype="float32", batch_input_shape=[None, 1, ..., name="input_1")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=32, use_bias=True, name="convolution2d_1", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(rate=0.2, trainable=True, name="dropout_1")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=32, use_bias=True, name="convolution2d_2", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your MaxPooling2D call to the Keras 2 API: MaxPooling2D(name="maxpooling2d_1", trainable=True, data_format="channels_first", pool_size=[2, 2], padding="valid", strides=[2, 2])
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=64, use_bias=True, name="convolution2d_3", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(rate=0.2, trainable=True, name="dropout_2")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=64, use_bias=True, name="convolution2d_4", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your MaxPooling2D call to the Keras 2 API: MaxPooling2D(name="maxpooling2d_2", trainable=True, data_format="channels_first", pool_size=[2, 2], padding="valid", strides=[2, 2])
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=128, use_bias=True, name="convolution2d_5", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(rate=0.2, trainable=True, name="dropout_3")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=128, use_bias=True, name="convolution2d_6", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: The Merge layer is deprecated and will be removed after 08/2017. Use instead layers from keras.layers.merge, e.g. add, concatenate, etc.
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=64, use_bias=True, name="convolution2d_7", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(rate=0.2, trainable=True, name="dropout_4")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=64, use_bias=True, name="convolution2d_8", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=32, use_bias=True, name="convolution2d_9", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(rate=0.2, trainable=True, name="dropout_5")
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=32, use_bias=True, name="convolution2d_10", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(3, 3))
return cls(**config)
/home/thviet/anaconda2/envs/retina/lib/python2.7/site-packages/keras/engine/topology.py:1252: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(kernel_initializer="glorot_uniform", kernel_constraint=None, activity_regularizer=None, trainable=True, padding="same", strides=[1, 1], filters=2, use_bias=True, name="convolution2d_11", bias_regularizer=None, bias_constraint=None, data_format="channels_first", kernel_regularizer=None, activation="relu", kernel_size=(1, 1))
return cls(**config)
2017-12-11 15:24:11.000932: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-12-11 15:24:11.000979: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-12-11 15:24:11.000987: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-12-11 15:24:11.000992: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-12-11 15:24:11.000998: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
.......................................................

Here is my keras.json
{
"image_data_format" : "channels_first",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "tensorflow"
}

from retina-unet.

from retina-unet.

I have the same problem

test PATCHES images shape:
(228900, 1, 48, 48)
test PATCHES images range (min-max): 0.0 - 1.0
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your InputLayer call to the Keras 2 API: InputLayer(batch_input_shape=[None, 1, ..., name="input_1", dtype="float32")
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_1", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=32, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(trainable=True, name="dropout_1", rate=0.2)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_2", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=32, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your MaxPooling2D call to the Keras 2 API: MaxPooling2D(name="maxpooling2d_1", trainable=True, pool_size=[2, 2], strides=[2, 2], padding="valid", data_format="channels_first")
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_3", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=64, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(trainable=True, name="dropout_2", rate=0.2)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_4", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=64, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your MaxPooling2D call to the Keras 2 API: MaxPooling2D(name="maxpooling2d_2", trainable=True, pool_size=[2, 2], strides=[2, 2], padding="valid", data_format="channels_first")
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_5", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=128, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(trainable=True, name="dropout_3", rate=0.2)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_6", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=128, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: The Merge layer is deprecated and will be removed after 08/2017. Use instead layers from keras.layers.merge, e.g. add, concatenate, etc.
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_7", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=64, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(trainable=True, name="dropout_4", rate=0.2)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_8", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=64, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_9", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=32, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Dropout call to the Keras 2 API: Dropout(trainable=True, name="dropout_5", rate=0.2)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_10", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(3, 3), filters=32, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
/home/saad/anaconda3/lib/python3.6/site-packages/keras/engine/topology.py:1269: UserWarning: Update your Conv2D call to the Keras 2 API: Conv2D(name="convolution2d_11", activity_regularizer=None, trainable=True, activation="relu", kernel_size=(1, 1), filters=2, strides=[1, 1], padding="same", data_format="channels_first", kernel_initializer="glorot_uniform", kernel_regularizer=None, bias_regularizer=None, kernel_constraint=None, bias_constraint=None, use_bias=True)
return cls(**config)
2018-02-08 13:25:04.736991: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-02-08 13:25:05.110080: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Found device 0 with properties:
name: TITAN Xp COLLECTORS EDITION major: 6 minor: 1 memoryClockRate(GHz): 1.582
pciBusID: 0000:03:00.0
totalMemory: 11.90GiB freeMemory: 11.25GiB
2018-02-08 13:25:05.110120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1120] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: TITAN Xp COLLECTORS EDITION, pci bus id: 0000:03:00.0, compute capability: 6.1)
2018-02-08 13:25:10.244735: E tensorflow/stream_executor/cuda/cuda_dnn.cc:378] Loaded runtime CuDNN library: 7005 (compatibility version 7000) but source was compiled with 6021 (compatibility version 6000). If using a binary install, upgrade your CuDNN library to match. If building from sources, make sure the library loaded at runtime matches a compatible version specified during compile configuration.
2018-02-08 13:25:10.245843: F tensorflow/core/kernels/conv_ops.cc:667] Check failed: stream->parent()->GetConvolveAlgorithms( conv_parameters.ShouldIncludeWinogradNonfusedAlgo(), &algorithms)
Aborted (core dumped)

from retina-unet.