We Keep Coding

How do I convert a model with two inputs?

Error converting pytorch model to coreml.
How do I convert a model with two inputs?
This model is style transfer.
var' was not implemented in the model, so it was searched and added. And an error occurred in 'var'.
var
#register_torch_op()
def var(context, node):
inputs = _get_inputs(context, node, expected=4)
x = inputs[0]
axes = inputs[1].val
print(inputs)
# Assert we can have biased divisor (N).
# An unbiased divisor (N - 1) would be much more complex,
# since we can't use reduce_mean. We therefore would need
# to otherwise do manual computation of the divisor for each axis.
assert (inputs[2].val == False)
keepdim = inputs[3].val
x_mean = mb.reduce_mean(x = x, axes = axes, keep_dims=keepdim)
x_sub_mean = mb.sub(x = x, y = x_mean)
x_sub_mean_square = mb.square(x = x_sub_mean)
x_var = mb.reduce_mean(x = x_sub_mean_square, axes = axes, keep_dims=keepdim)
context.add(x_var, torch_name=node.name)
code
import coremltools as ct
import urllib
import torch
import torch.nn as nn
import torchvision
from PIL import Image
from torchvision import transforms
from model import Model, AdaIN
class ConvertModel(nn.Module):
def __init__(self):
super(ConvertModel, self).__init__()
self.model = Model()
self.model.decoder.state_dict(torch.load('./models/decoder_3.pth', map_location='cpu'))
self.model.encoder
def forward(self, content, style, alpha=0.6):
content_f = self.model.encoder(content)
style_f = self.model.encoder(style)
feat = AdaIN(content_f, style_f)
feat = feat * alpha + content_f * (1 - alpha)
return self.model.decoder(feat)
model = ConvertModel()
dummy_input = torch.rand(1, 3, 512, 512)
traced_model = torch.jit.trace(model, (dummy_input, dummy_input))
input_content = ct.ImageType(name='content', shape=(1, 3, 512, 512),
bias=[-0.485/0.229, -0.456/0.224, -0.406/0.225], scale=1./(0.226*255.0))
input_style = ct.ImageType(name='style', shape=(1, 3, 512, 512),
bias=[-0.485/0.229, -0.456/0.224, -0.406/0.225], scale=1./(0.226*255.0))
coreml_model = ct.convert(traced_model, inputs=[input_content, input_style])
spec = coreml_model.get_spec()
ct.utils.rename_feature(spec, "current", "output")
coreml_model_updated = ct.models.MLModel(spec)
coreml_model_updated.save('style_transfer.mlmodel')
log
WARNING:root:Torch version 1.11.0 has not been tested with coremltools. You may run into unexpected errors. Torch 1.10.2 is the most recent version that has been tested.
Converting Frontend ==> MIL Ops: 54%|█████▎ | 197/367 [00:00<00:00, 2564.34 ops/s]
Traceback (most recent call last):
File "/Users/sinmugyeol/deeplearning/generator_model/style_transfer/convert2coreml.py", line 36, in <module>
coreml_model = ct.convert(traced_model, inputs=[input_content, input_style])
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/_converters_entry.py", line 352, in convert
mlmodel = mil_convert(
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/converter.py", line 183, in mil_convert
return _mil_convert(model, convert_from, convert_to, ConverterRegistry, MLModel, compute_units, **kwargs)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/converter.py", line 210, in _mil_convert
proto, mil_program = mil_convert_to_proto(
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/converter.py", line 273, in mil_convert_to_proto
prog = frontend_converter(model, **kwargs)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/converter.py", line 105, in __call__
return load(*args, **kwargs)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/frontend/torch/load.py", line 47, in load
return _perform_torch_convert(converter, debug)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/frontend/torch/load.py", line 84, in _perform_torch_convert
prog = converter.convert()
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/frontend/torch/converter.py", line 250, in convert
convert_nodes(self.context, self.graph)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/frontend/torch/ops.py", line 89, in convert_nodes
add_op(context, node)
File "/Users/sinmugyeol/opt/anaconda3/envs/core/lib/python3.10/site-packages/coremltools/converters/mil/frontend/torch/ops.py", line 256, in var
assert (inputs[2].val == False)
AssertionError
macOS Monterey 12.3.1 M1.
python 3.10.4.
pytorch 1.11.0.
coremltools 5.2.0.
numpy 1.21.5.

Exporting a model with tf.map_fn

I have some tensorflow model which I need to export in a saved model. Below is the simplified code of the model, which I am trying to export.
import tensorflow as tf
def foo(x):
return tf.reduce_sum(x)
inputs = tf.keras.layers.Input(shape=(128,128,3))
y = tf.keras.layers.Conv2D(filters=32, kernel_size=3, padding='SAME')(inputs)
y = tf.keras.layers.ReLU()(y)
outputs = tf.map_fn(foo, y, dtype=(tf.float32))
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)
model.save('./export', save_format='tf')
but while exporting the model I am getting the following error.
/Users/bruce/.venv/bin/python /Users/bruce/test_project/mymodel/test.py
Traceback (most recent call last):
File "/Users/bruce/test_project/mymodel/test.py", line 12, in <module>
outputs = tf.map_fn(foo, y, dtype=(tf.float32))
File "/Users/bruce/.venv/lib/python3.6/site-packages/tensorflow_core/python/ops/map_fn.py", line 228, in map_fn
for elem in elems_flat]
File "/Users/bruce/.venv/lib/python3.6/site-packages/tensorflow_core/python/ops/map_fn.py", line 228, in <listcomp>
for elem in elems_flat]
File "/Users/bruce/.venv/lib/python3.6/site-packages/tensorflow_core/python/ops/tensor_array_ops.py", line 1078, in __init__
name=name)
File "/Users/bruce/.venv/lib/python3.6/site-packages/tensorflow_core/python/ops/tensor_array_ops.py", line 716, in __init__
self._tensor_array = [None for _ in range(size)]
TypeError: 'Tensor' object cannot be interpreted as an integer
I cannot remove the part tf.map_fn which is doing some essential processing which I need in the saved model while deploying it.

You need to use a custom layer:
class MyMapLayer(tf.keras.layers.Layer):
def __init__(*args, **kwargs)
super().__init__(*args, **kwargs)
def foo(self, x):
return tf.reduce_sum(x)
def call(self, inputs, **kwargs):
return tf.map_fn(self.foo, inputs, dtype=(tf.float32))
Then, in your model:
inputs = tf.keras.layers.Input(shape=(128,128,3))
y = tf.keras.layers.Conv2D(filters=32, kernel_size=3, padding='SAME')(inputs)
y = tf.keras.layers.ReLU()(y)
outputs = MyMapLayer()(y)
model = tf.keras.models.Model(inputs=inputs, outputs=outputs)

Unable to use MSE of VGG features in loss function

I'm using keras (tf.keras) in tensorflow 2.0.0
I've a network, whose input is an image and output is also an image. I want to use a combination of MSE, MSE in VGG feature space and some other losses, which depend on intermediate layer output. I'm defining a custom loss function. I'm able to build the model, compile with the custom loss. But when I train using fit_generator, I'm getting a SymbolicException saying Inputs to eager execution function cannot be Keras symbolic tensors
Full Code:
Train File:
def __init__(self, gray_images: bool, verbose: bool = True):
super().__init__(gray_images, verbose)
self.model = None
self.vgg_feature_extractor = VggFeaturesExtractor(model_name='vgg16', layers=[3, 6, 10])
def build_model():
image_input = Input(shape=(None, None, num_input_channels))
out1 = self.build_out1_model(image_input, num_filters, depth_t)
out2 = self.build_out2_model(image_input, num_filters, depth_n, use_bnorm)
enhanced_image = ... # Some function of image_input, out1 and out2
self.model = Model(inputs=image_input, outputs=enhanced_image)
self.model.add_loss(loss_weights[1] * self.loss2(out2))
self.model.compile(optimizer='adam', loss=self.vgg_loss)
def vgg_loss(self, gt_image, est_image):
gt_features = self.vgg_feature_extractor.extract_features(gt_image)
est_features = self.vgg_feature_extractor.extract_features(est_image)
loss = tf.reduce_mean(tf.square(gt_features[0] - est_features[0])) + \
tf.reduce_mean(tf.square(gt_features[1] - est_features[1])) + \
tf.reduce_mean(tf.square(gt_features[2] - est_features[2]))
return loss
VggFeatures.py:
class VggFeaturesExtractor:
def __init__(self, model_name: str, layers: List[int]):
self.model_name = model_name
self.layers = layers
if model_name == 'vgg16':
from tensorflow.keras.applications.vgg16 import VGG16, preprocess_input
vgg_model = VGG16(include_top=False)
self.preprocess_input = preprocess_input
elif model_name == 'vgg19':
from tensorflow.keras.applications.vgg19 import VGG19, preprocess_input
vgg_model = VGG19(include_top=False)
self.preprocess_input = preprocess_input
else:
raise RuntimeError(f'Unknown Model: {model_name}')
outputs = []
for layer_num in layers:
outputs.append(vgg_model.layers[layer_num].output)
self.feature_extractor = keras.Model(inputs=vgg_model.input, outputs=outputs)
def extract_features(self, images: numpy.ndarray):
preprocessed_images = self.preprocess_input(images)
features = self.feature_extractor(preprocessed_images)
return features
Stack trace:
Epoch 1/1000
Traceback (most recent call last):
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py", line 61, in quick_execute
num_outputs)
TypeError: An op outside of the function building code is being passed
a "Graph" tensor. It is possible to have Graph tensors
leak out of the function building context by including a
tf.init_scope in your function building code.
For example, the following function will fail:
#tf.function
def has_init_scope():
my_constant = tf.constant(1.)
with tf.init_scope():
added = my_constant * 2
The graph tensor has name: StridedSliceGrad:0
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/media/nagabhushan/Data02/SNB/IISc/Research/.../Workspace/Ideas/01_Supervised/src/N09.py", line 363, in <module>
main()
File "/media/nagabhushan/Data02/SNB/IISc/Research/.../Workspace/Ideas/01_Supervised/src/N09.py", line 343, in main
args.save_interval)
File "/media/nagabhushan/Data02/SNB/IISc/Research/.../Workspace/Ideas/01_Supervised/src/N09.py", line 92, in train_model
verbose=self.verbose)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 1297, in fit_generator
steps_name='steps_per_epoch')
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_generator.py", line 265, in model_iteration
batch_outs = batch_function(*batch_data)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 973, in train_on_batch
class_weight=class_weight, reset_metrics=reset_metrics)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_v2_utils.py", line 264, in train_on_batch
output_loss_metrics=model._output_loss_metrics)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py", line 311, in train_on_batch
output_loss_metrics=output_loss_metrics))
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_eager.py", line 268, in _process_single_batch
grads = tape.gradient(scaled_total_loss, trainable_weights)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/backprop.py", line 1014, in gradient
unconnected_gradients=unconnected_gradients)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/imperative_grad.py", line 76, in imperative_grad
compat.as_str(unconnected_gradients.value))
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 911, in _backward_function_wrapper
processed_args, remapped_captures)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 1224, in _call_flat
ctx, args, cancellation_manager=cancellation_manager)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/function.py", line 511, in call
ctx=ctx)
File "/media/nagabhushan/Data02/SoftwareFiles/Anaconda/anaconda3/envs/.../lib/python3.7/site-packages/tensorflow_core/python/eager/execute.py", line 75, in quick_execute
"tensors, but found {}".format(keras_symbolic_tensors))
tensorflow.python.eager.core._SymbolicException: Inputs to eager execution function cannot be Keras symbolic tensors, but found [<tf.Tensor 'StridedSliceGrad:0' shape=(16, 64, 64, 3) dtype=float32>]
Process finished with exit code 1
Note:
1. If I replace self.model.compile(optimizer='adam', loss=self.vgg_loss) with self.model.compile(optimizer='adam', loss='mse'), code works fine, which implies the other part of code is working correctly.
2. Almost every question I found on SO regarding VGG loss advises to append VGG network to the main network, set trainable=False for VGG network and then train with MSE loss. But I can't do that, since I have many components in my loss function.

I was able to fix this issue by disabling eager execution. In tensorflow 2.0, eager execution is enabled by default.
tf.compat.v1.disable_eager_execution()
I didn't understand how this was able to fix the issue though. If anybody stumbles on a similar problem, you can try disabling eager execution.

Tensorflow model.fit() using a Dataset generator

I am using the Dataset API to generate training data and sort it into batches for a NN.
Here is a minimum working example of my code:
import tensorflow as tf
import numpy as np
import random
def my_generator():
while True:
x = np.random.rand(4, 20)
y = random.randint(0, 11)
label = tf.one_hot(y, depth=12)
yield x.reshape(4, 20, 1), label
def my_input_fn():
dataset = tf.data.Dataset.from_generator(lambda: my_generator(),
output_types=(tf.float64, tf.int32))
dataset = dataset.batch(32)
iterator = dataset.make_one_shot_iterator()
batch_features, batch_labels = iterator.get_next()
return batch_features, batch_labels
if __name__ == "__main__":
tf.enable_eager_execution()
model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
tf.keras.layers.Dense(128, activation=tf.nn.relu),
tf.keras.layers.Dense(12, activation=tf.nn.softmax)])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
data_generator = my_input_fn()
model.fit(data_generator)
The code fails using TensorFlow 1.13.1 at the model.fit() call with the following error:
Traceback (most recent call last):
File "scripts/min_working_example.py", line 37, in <module>
model.fit(data_generator)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 880, in fit
validation_steps=validation_steps)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_arrays.py", line 310, in model_iteration
ins_batch = slice_arrays(ins[:-1], batch_ids) + [ins[-1]]
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 526, in slice_arrays
return [None if x is None else x[start] for x in arrays]
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 526, in <listcomp>
return [None if x is None else x[start] for x in arrays]
File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 654, in _slice_helper
name=name)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 820, in strided_slice
shrink_axis_mask=shrink_axis_mask)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 9334, in strided_slice
_six.raise_from(_core._status_to_exception(e.code, message), None)
File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError: Attr shrink_axis_mask has value 4294967295 out of range for an int32 [Op:StridedSlice] name: strided_slice/
I tried running the same code on a different machine using TensorFlow 2.0 (after removing the line tf.enable_eager_execution() because it runs eagerly by default) and I got the following error:
Traceback (most recent call last):
File "scripts/min_working_example.py", line 37, in <module>
model.fit(data_generator)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 873, in fit
steps_name='steps_per_epoch')
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_arrays.py", line 352, in model_iteration
batch_outs = f(ins_batch)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/backend.py", line 3217, in __call__
outputs = self._graph_fn(*converted_inputs)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 558, in __call__
return self._call_flat(args)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 627, in _call_flat
outputs = self._inference_function.call(ctx, args)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/eager/function.py", line 397, in call
(len(args), len(list(self.signature.input_arg))))
ValueError: Arguments and signature arguments do not match: 21 23
I tried changing model.fit() to model.fit_generator() but this fails on both TensorFlow versions too. On TF 1.13.1 I get the following error:
Traceback (most recent call last):
File "scripts/min_working_example.py", line 37, in <module>
model.fit_generator(data_generator)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 1426, in fit_generator
initial_epoch=initial_epoch)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 115, in model_iteration
shuffle=shuffle)
File "~/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training_generator.py", line 377, in convert_to_generator_like
num_samples = int(nest.flatten(data)[0].shape[0])
TypeError: __int__ returned non-int (type NoneType)
and on TF 2.0 I get the following error:
Traceback (most recent call last):
File "scripts/min_working_example.py", line 37, in <module>
model.fit_generator(data_generator)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training.py", line 1515, in fit_generator
steps_name='steps_per_epoch')
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 140, in model_iteration
shuffle=shuffle)
File "~/.local/lib/python3.7/site-packages/tensorflow/python/keras/engine/training_generator.py", line 477, in convert_to_generator_like
raise ValueError('You must specify `batch_size`')
ValueError: You must specify `batch_size`
yet batch_size is not a recognized keyword for fit_generator().
I am puzzled by these error messages and I would appreciate if anyone can shed some light on them, or point out what I am doing wrong.

While the origin of the errors is still nebulous, I have found a solution that makes the code work. I'll post it here in case it is useful to anyone in a similar situation.
Basically, I changed the my_input_fn() into a generator and used model.fit_generator() as follows:
import tensorflow as tf
import numpy as np
import random
def my_generator(total_items):
i = 0
while i < total_items:
x = np.random.rand(4, 20)
y = random.randint(0, 11)
label = tf.one_hot(y, depth=12)
yield x.reshape(4, 20, 1), label
i += 1
def my_input_fn(total_items, epochs):
dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
output_types=(tf.float64, tf.int64))
dataset = dataset.repeat(epochs)
dataset = dataset.batch(32)
iterator = dataset.make_one_shot_iterator()
while True:
batch_features, batch_labels = iterator.get_next()
yield batch_features, batch_labels
if __name__ == "__main__":
tf.enable_eager_execution()
model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
tf.keras.layers.Dense(64, activation=tf.nn.relu),
tf.keras.layers.Dense(12, activation=tf.nn.softmax)])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
total_items = 200
batch_size = 32
epochs = 10
num_batches = int(total_items/batch_size)
train_data_generator = my_input_fn(total_items, epochs)
model.fit_generator(generator=train_data_generator, steps_per_epoch=num_batches, epochs=epochs, verbose=1)
EDIT
As implied by giser_yugang in a comment, it is also possible to do it with my_input_fn() as a function returning the dataset instead of the individual batches.
def my_input_fn(total_items, epochs):
dataset = tf.data.Dataset.from_generator(lambda: my_generator(total_items),
output_types=(tf.float64, tf.int64))
dataset = dataset.repeat(epochs)
dataset = dataset.batch(32)
return dataset
if __name__ == "__main__":
tf.enable_eager_execution()
model = tf.keras.Sequential([tf.keras.layers.Flatten(input_shape=(4, 20, 1)),
tf.keras.layers.Dense(64, activation=tf.nn.relu),
tf.keras.layers.Dense(12, activation=tf.nn.softmax)])
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
total_items = 100
batch_size = 32
epochs = 10
num_batches = int(total_items/batch_size)
dataset = my_input_fn(total_items, epochs)
model.fit_generator(dataset, epochs=epochs, steps_per_epoch=num_batches)
There does not appear to be any average performance difference between the approaches.

Cannot add SPP layer in CNN using Keras

I want to apply Spatial Pyramid Pooling before the Dense layer in a CNN.
I used Keras for implementation.
Tensorflow was used as a backend.
However, I got an error.
What's wrong with my code? Thank you.
Traceback (most recent call last):
File "<pyshell#25>", line 1, in <module>
model.add(SpatialPyramidPooling(pooling_regions, input_shape=Input(shape = (None,None,None,3))))
File "C:\Program Files\Python36\lib\site-packages\spp\SpatialPyramidPooling.py", line 33, in __init__
super(SpatialPyramidPooling, self).__init__(**kwargs)
File "C:\Program Files\Python36\lib\site-packages\keras\engine\topology.py", line 311, in __init__
batch_input_shape = (batch_size,) + tuple(kwargs['input_shape'])
File "C:\Program Files\Python36\lib\site-packages\tensorflow\python\framework\ops.py", line 439, in __iter__
"Tensor objects are not iterable when eager execution is not "
TypeError: Tensor objects are not iterable when eager execution is not enabled. To iterate over this tensor use tf.map_fn.
Here is the code:
from keras.engine.topology import Layer
from keras.models import Sequential
import keras.backend as K
import numpy as np
model = Sequential()
model.add(SpatialPyramidPooling((1,2,4), Input(shape=(None, None, None, 3))))
class SpatialPyramidPooling(Layer):
def __init__(self, pool_list, **kwargs):
self.dim_ordering = K.image_dim_ordering()
assert self.dim_ordering in {'tf', 'th'}, 'dim_ordering must be in {tf, th}'
self.pool_list = pool_list
self.num_outputs_per_channel = sum([i * i for i in pool_list])
super(SpatialPyramidPooling, self).__init__(**kwargs)
def call(self, x, mask=None):
input_shape = K.shape(x)
print(input_shape)
print(K.eval(input_shape))
outputs = K.variable(value=np.random.random((3,4)))
return outputs

I'm pretty sure you should be using input_shape=(None,None,None,3) instead of input_shape=Input(shape = (None,None,None,3))
Also, you cannot use any function that demands the presence of data in the call method. You're using K.shape and K.eval, both will bring you errors in compilation.
If you need information about the input shape, you have to do it in the def build(self, input_shape): method.