Exercise 3 - unet_model

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi
I have written this code and based on previous instruction I think its right. I can’t troubleshoot the error. would you help me?

Error:

ValueError Traceback (most recent call last)
in
4 num_channels = 3
5
----> 6 unet = unet_model((img_height, img_width, num_channels))
7 comparator(summary(unet), outputs.unet_model_output)

in unet_model(input_size, n_filters, n_classes)
16 # Add a conv_block with the inputs of the unet_ model and n_filters
17 ### START CODE HERE
—> 18 cblock1 = conv_block(input_size, n_filters)
19 # Chain the first element of the output of each block to be the input of the next conv_block.
20 # Double the number of filters at each new step

in conv_block(inputs, n_filters, dropout_prob, max_pooling)
19 activation=‘relu’,
20 padding=‘same’,
—> 21 kernel_initializer=‘he_normal’)(inputs)
22 conv = Conv2D(n_filters, # Number of filters
23 kernel_size = (3,3), # Kernel size

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in call(self, *args, **kwargs)
980 with ops.name_scope_v2(name_scope):
981 if not self.built:
→ 982 self._maybe_build(inputs)
983
984 with ops.enable_auto_cast_variables(self._compute_dtype_object):

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _maybe_build(self, inputs)
2616 if not self.built:
2617 input_spec.assert_input_compatibility(
→ 2618 self.input_spec, inputs, self.name)
2619 input_list = nest.flatten(inputs)
2620 if input_list and self._dtype_policy.compute_dtype is None:

/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
156 str(len(input_spec)) + ’ inputs, ’
157 'but it received ’ + str(len(inputs)) +
→ 158 ’ input tensors. Inputs received: ’ + str(inputs))
159 for input_index, (x, spec) in enumerate(zip(inputs, input_spec)):
160 if spec is None:

ValueError: Layer conv2d_47 expects 1 inputs, but it received 3 input tensors. Inputs received: [<tf.Tensor: shape=(), dtype=int32, numpy=96>, <tf.Tensor: shape=(), dtype=int32, numpy=128>, <tf.Tensor: shape=(), dtype=int32, numpy=3>]

2

Please do not post your code on the Forums. That isn’t allowed by the Honor Code. Please edit your message and remove the code.

Your cblock1 should use “inputs”, not “input_size”.

I did not read any farther - check your code for similar errors (where your code doesn’t flow the data between layers).

3

Thanks for your response. I removed the code