I'm trying to use a auto-encoder on time series. When I use padding on the data all is working, but when I'm using variable data length I have small data shape issues: Incompatible shapes: [1,125,4] vs. [1,126,4]
input_series = Input(shape=(None, 4))
x = Conv1D(4, 2, activation='relu', padding='same')(input_series)
x = MaxPooling1D(1, padding='same')(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
x = MaxPooling1D(1, padding='same')(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
encoder = MaxPooling1D(1, padding='same', name='encoder')(x)
x = Conv1D(4, 3, activation='relu', padding='same')(encoder)
x = UpSampling1D(1)(x)
x = Conv1D(4, 3, activation='relu', padding='same')(x)
x = UpSampling1D(1)(x)
x = Conv1D(16, 2, activation='relu')(x)
x = UpSampling1D(1)(x)
decoder = Conv1D(4, 2, activation='sigmoid', padding='same')(x)
autoencoder = Model(input_series, decoder)
autoencoder.compile(loss='mse', optimizer='adam')
autoencoder.summary()
Summary:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_25 (InputLayer) (None, None, 4) 0
_________________________________________________________________
conv1d_169 (Conv1D) (None, None, 4) 36
_________________________________________________________________
max_pooling1d_49 (MaxPooling (None, None, 4) 0
_________________________________________________________________
conv1d_170 (Conv1D) (None, None, 4) 52
_________________________________________________________________
max_pooling1d_50 (MaxPooling (None, None, 4) 0
_________________________________________________________________
conv1d_171 (Conv1D) (None, None, 4) 52
_________________________________________________________________
encoder (MaxPooling1D) (None, None, 4) 0
_________________________________________________________________
conv1d_172 (Conv1D) (None, None, 4) 52
_________________________________________________________________
up_sampling1d_73 (UpSampling (None, None, 4) 0
_________________________________________________________________
conv1d_173 (Conv1D) (None, None, 4) 52
_________________________________________________________________
up_sampling1d_74 (UpSampling (None, None, 4) 0
_________________________________________________________________
conv1d_174 (Conv1D) (None, None, 16) 144
_________________________________________________________________
up_sampling1d_75 (UpSampling (None, None, 16) 0
_________________________________________________________________
conv1d_175 (Conv1D) (None, None, 4) 132
=================================================================
Total params: 520
Trainable params: 520
Non-trainable params: 0
_________________________________________________________________
Error:
Epoch 1/50
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1321 try:
-> 1322 return fn(*args)
1323 except errors.OpError as e:
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1306 return self._call_tf_sessionrun(
-> 1307 options, feed_dict, fetch_list, target_list, run_metadata)
1308
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1408 self._session, options, feed_dict, fetch_list, target_list,
-> 1409 run_metadata)
1410 else:
InvalidArgumentError: Incompatible shapes: [1,125,4] vs. [1,126,4]
[[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:#training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
[[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-101-a6e405699326> in <module>()
6 train_generator(X_train),
7 epochs=50,
----> 8 steps_per_epoch=len(X_train))
9
10
C:\ProgramData\Anaconda3\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name +
90 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in fit_generator(self, generator, steps_per_epoch, epochs, verbose, callbacks, validation_data, validation_steps, class_weight, max_queue_size, workers, use_multiprocessing, shuffle, initial_epoch)
2228 outs = self.train_on_batch(x, y,
2229 sample_weight=sample_weight,
-> 2230 class_weight=class_weight)
2231
2232 if not isinstance(outs, list):
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in train_on_batch(self, x, y, sample_weight, class_weight)
1881 ins = x + y + sample_weights
1882 self._make_train_function()
-> 1883 outputs = self.train_function(ins)
1884 if len(outputs) == 1:
1885 return outputs[0]
C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py in __call__(self, inputs)
2480 session = get_session()
2481 updated = session.run(fetches=fetches, feed_dict=feed_dict,
-> 2482 **self.session_kwargs)
2483 return updated[:len(self.outputs)]
2484
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
898 try:
899 result = self._run(None, fetches, feed_dict, options_ptr,
--> 900 run_metadata_ptr)
901 if run_metadata:
902 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1133 if final_fetches or final_targets or (handle and feed_dict_tensor):
1134 results = self._do_run(handle, final_targets, final_fetches,
-> 1135 feed_dict_tensor, options, run_metadata)
1136 else:
1137 results = []
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1314 if handle is None:
1315 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1316 run_metadata)
1317 else:
1318 return self._do_call(_prun_fn, handle, feeds, fetches)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
1333 except KeyError:
1334 pass
-> 1335 raise type(e)(node_def, op, message)
1336
1337 def _extend_graph(self):
InvalidArgumentError: Incompatible shapes: [1,125,4] vs. [1,126,4]
[[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:#training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
[[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
Caused by op 'loss_22/conv1d_175_loss/sub', defined at:
File "C:\ProgramData\Anaconda3\lib\runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "C:\ProgramData\Anaconda3\lib\runpy.py", line 85, in _run_code
exec(code, run_globals)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "C:\ProgramData\Anaconda3\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
app.start()
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 478, in start
self.io_loop.start()
File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
super(ZMQIOLoop, self).start()
File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
self._handle_recv()
File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
self._run_callback(callback, msg)
File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
callback(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2728, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2850, in run_ast_nodes
if self.run_code(code, result):
File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-100-ddd3b57d5f0b>", line 22, in <module>
autoencoder.compile(loss='mse', optimizer='adam')
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 830, in compile
sample_weight, mask)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 429, in weighted
score_array = fn(y_true, y_pred)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py", line 14, in mean_squared_error
return K.mean(K.square(y_pred - y_true), axis=-1)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\math_ops.py", line 979, in binary_op_wrapper
return func(x, y, name=name)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_math_ops.py", line 8582, in sub
"Sub", x=x, y=y, name=name)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3392, in create_op
op_def=op_def)
File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1718, in __init__
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access
InvalidArgumentError (see above for traceback): Incompatible shapes: [1,125,4] vs. [1,126,4]
[[Node: loss_22/conv1d_175_loss/sub = Sub[T=DT_FLOAT, _class=["loc:#training_18/Adam/gradients/loss_22/conv1d_175_loss/sub_grad/Reshape"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1d_175/Sigmoid, _arg_conv1d_175_target_0_1/_4489)]]
[[Node: loss_22/mul/_4613 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_1245_loss_22/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]
One of your Conv1D layers is not using padding='same'.
But there is something very weird there: why would you use MaxPooling with pool_size=1? It does nothing.
Now suppose you use pool_size=2, then you'd need to pad the inputs anyway, because you'd need inputs with length multiple of 8 (2³) to be able to end up with the same shape after the upsamplings.
For a variable length autoencoder, there is an example here: Variable length output in keras
For all effects, LSTM layers treat shapes exactly the same way Conv1D layers do.
Related
Encountered the error while trying to fit model of encoder-decoder using ConvLSTM2D. the x_train is of shape (31567, 7, 210, 203, 1)(batch_size,framelength,H,W,C).
The encoder part works when executed in isolation but the error occurs when i add the decoder part, seems like the problem is in the input part of decoder but not sure.
tried reshaping the encoder_state_c_1 and encoder_state_h_1 to 5D before passing it to the decoder ConvLSTM2D but doesn't help either.
Please find the code and error here:
MODEL
def define_models_1_moving_1(framelength, n_filter, filter_size):
# define training encoder
encoder_inputs = Input(name = "encoder_input",
shape=(x_train.shape[1], x_train.shape[2], x_train.shape[3], x_train.shape[4]))
encoder_1 = ConvLSTM2D(name = "encoder_ConvLSTM",
filters = n_filter, kernel_size=filter_size, padding='same', return_sequences=True, return_state=True,
kernel_regularizer=l2(0.0005), recurrent_regularizer=l2(0.0005), bias_regularizer=l2(0.0005))
# input_shape=(x_train.shape[1], x_train.shape[2], x_train.shape[3], x_train.shape[4]))
encoder_outputs_1, encoder_state_h_1, encoder_state_c_1 = encoder_1(encoder_inputs)
# define training decoder
decoder_inputs = Input(name = "decoder_input",
shape=(x_train.shape[1], x_train.shape[2], x_train.shape[3], x_train.shape[4]))
decoder_1 = ConvLSTM2D(name = "decoder_ConvLSTM",
filters=n_filter, kernel_size=filter_size, padding='same', return_sequences=True, return_state=True,
kernel_regularizer=l2(0.0005), recurrent_regularizer=l2(0.0005), bias_regularizer=l2(0.0005))
decoder_outputs_1, _, _ = decoder_1([decoder_inputs, encoder_state_h_1, encoder_state_c_1]) #### This line is giving Error
model = Model([encoder_inputs, decoder_inputs], decoder_outputs_1)
return model
Error
Traceback (most recent call last):
File "D:\Chintan\Dataset\model.py", line 155, in
training_history = train_1_moving_1.fit(
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\Admin\AppData\Local\Temp_autograph_generated_filernuwcygs.py", line 15, in tf__train_function
retval = ag__.converted_call(ag__.ld(step_function), (ag__.ld(self), ag__.ld(iterator)), None, fscope)
ValueError: in user code:
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1249, in train_function *
return step_function(self, iterator)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1233, in step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1222, in run_step **
outputs = model.train_step(data)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py", line 1023, in train_step
y_pred = self(x, training=True)
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\input_spec.py", line 216, in assert_input_compatibility
raise ValueError(
ValueError: Layer "model_120" expects 2 input(s), but it received 1 input tensors. Inputs received: [<tf.Tensor 'IteratorGetNext:0' shape=(None, None, None, None, None) dtype=float32>]
I am building a prediction model for the sequence data using conv1d layer provided by Keras. This is how I did
model= Sequential()
model.add(Conv1D(60,32, strides=1, activation='relu',padding='causal',input_shape=(None,64,1)))
model.add(Conv1D(80,10, strides=1, activation='relu',padding='causal'))
model.add(Dropout(0.25))
model.add(Conv1D(100,5, strides=1, activation='relu',padding='causal'))
model.add(MaxPooling1D(1))
model.add(Dropout(0.25))
model.add(Dense(300,activation='relu'))
model.add(Dense(1,activation='relu'))
print(model.summary())
However, the debugging information has
Traceback (most recent call last):
File "processing_2a_1.py", line 96, in <module>
model.add(Conv1D(60,32, strides=1, activation='relu',padding='causal',input_shape=(None,64,1)))
File "build/bdist.linux-x86_64/egg/keras/models.py", line 442, in add
File "build/bdist.linux-x86_64/egg/keras/engine/topology.py", line 558, in __call__
File "build/bdist.linux-x86_64/egg/keras/engine/topology.py", line 457, in assert_input_compatibility
ValueError: Input 0 is incompatible with layer conv1d_1: expected ndim=3, found ndim=4
The training data and validation data shape are as follows
('X_train shape ', (1496000, 64, 1))
('Y_train shape ', (1496000, 1))
('X_val shape ', (374000, 64, 1))
('Y_val shape ', (374000, 1))
I think the input_shape in the first layer was not setup right. How to set it up?
Update: After using input_shape=(64,1), I got the following error message, even though the model summary runs through
________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d_1 (Conv1D) (None, 64, 60) 1980
_________________________________________________________________
conv1d_2 (Conv1D) (None, 64, 80) 48080
_________________________________________________________________
dropout_1 (Dropout) (None, 64, 80) 0
_________________________________________________________________
conv1d_3 (Conv1D) (None, 64, 100) 40100
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 64, 100) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64, 100) 0
_________________________________________________________________
dense_1 (Dense) (None, 64, 300) 30300
_________________________________________________________________
dense_2 (Dense) (None, 64, 1) 301
=================================================================
Total params: 120,761
Trainable params: 120,761
Non-trainable params: 0
_________________________________________________________________
None
Traceback (most recent call last):
File "processing_2a_1.py", line 125, in <module>
history=model.fit(X_train, Y_train, batch_size=batch_size, validation_data=(X_val,Y_val), epochs=nr_of_epochs,verbose=2)
File "build/bdist.linux-x86_64/egg/keras/models.py", line 871, in fit
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 1524, in fit
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 1382, in _standardize_user_data
File "build/bdist.linux-x86_64/egg/keras/engine/training.py", line 132, in _standardize_input_data
ValueError: Error when checking target: expected dense_2 to have 3 dimensions, but got array with shape (1496000, 1)
You should either change input_shape to
input_shape=(64,1)
... or use batch_input_shape:
batch_input_shape=(None, 64, 1)
This discussion explains the difference between the two in keras in detail.
I had the same issue. I found expanding the dimensions of the input data fixed it using tf.expand_dims
x = expand_dims(x, axis=-1)
I my case I wanted to use Conv2D on a single 20*32 feature map, and did:
print(kws_x_train.shape) # (8000,20,32)
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(16, (3, 8), input_shape=(20,32)),
])
...
model.fit(kws_x_train, kws_y_train, epochs=15)
which gives the expected ndim=4, found ndim=3. Full shape received: [None, 20, 32]. However you need to tell Conv2D that there is only 1 feature map, and add an extra dimension to the input vector. This worked:
kws_x_train2 = kws_x_train.reshape(kws_x_train.shape + (1,))
print(kws_x_train2.shape) # (8000,20,32,1)
model = tf.keras.models.Sequential([
tf.keras.layers.Conv2D(16, (3, 8), input_shape=(20,32,1)),
])
...
model.fit(kws_x_train2, kws_y_train, epochs=15)
Hi Can anyone help me out with the error, I have seemed to search through the documentation but to no avail.
The aim is to predict a time series. I have used a dummy data shape = (N, timesteps, features). I wish to predict x_2 from x_1, x_3 from x_2 and so on till x_11 from x_10 using LSTM. (Any suggestion to do it better is welcome). The output (below) shows the expected output shapes which seem correct. However, the error mentions an input dimension mismatch. As per documentation, I can't seem to find the problem.
import numpy as np
N = 13*12;
T = 10;
F = 3;
X = np.random.rand(N, T, F);
Y = np.random.rand(N, 1, F);
Y = np.concatenate((X[:,1:T,:], Y), axis=1);
import keras
from keras.models import Model
from keras.layers import Dense, Input, LSTM, Lambda, concatenate, Dropout
from keras.optimizers import Adam, SGD
from keras import regularizers
from keras.metrics import categorical_accuracy
from keras.models import load_model
input_ = Input(shape = (T, F), name ='input');
x = Dense(15, activation='sigmoid', name='fc1')(input_);
x = LSTM(25, return_sequences=True, activation='tanh', name='lstm')(x);
x = Dense(F, activation='sigmoid', name='fc2')(x);
model = Model(input_, x, name='dummy');
model.compile(optimizer='rmsprop', loss='mse', metrics=['accuracy']);
print(model.input_shape); print(X.shape);
print(model.output_shape); print(Y.shape);
print(model.summary());
model.fit(X, Y, batch_size = 13, epochs=30, validation_split=0.20, shuffle=False);
The error comes as
Using Theano backend.
(None, 10, 3)
(156, 10, 3)
(None, 10, 3)
(156, 10, 3)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input (InputLayer) (None, 10, 3) 0
_________________________________________________________________
fc1 (Dense) (None, 10, 15) 60
_________________________________________________________________
lstm (LSTM) (None, 10, 25) 4100
_________________________________________________________________
fc2 (Dense) (None, 10, 3) 78
=================================================================
Total params: 4,238
Trainable params: 4,238
Non-trainable params: 0
_________________________________________________________________
None
Train on 124 samples, validate on 32 samples
Epoch 1/30
Traceback (most recent call last):
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 903, in __call__
self.fn() if output_subset is None else\
ValueError: Input dimension mis-match. (input[0].shape[1] = 10, input[1].shape[1] = 15)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "b.py", line 34, in <module>
model.fit(X, Y, batch_size = 13, epochs=30, validation_split=0.20, shuffle=False);
File "C:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1498, in fit
initial_epoch=initial_epoch)
File "C:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1152, in _fit_loop
outs = f(ins_batch)
File "C:\Anaconda3\lib\site-packages\keras\backend\theano_backend.py", line 1158, in __call__
return self.function(*inputs)
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 917, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "C:\Anaconda3\lib\site-packages\theano\gof\link.py", line 325, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "C:\Anaconda3\lib\site-packages\six.py", line 692, in reraise
raise value.with_traceback(tb)
File "C:\Anaconda3\lib\site-packages\theano\compile\function_module.py", line 903, in __call__
self.fn() if output_subset is None else\
ValueError: Input dimension mis-match. (input[0].shape[1] = 10, input[1].shape[1] = 15)
Apply node that caused the error: Elemwise{Add}[(0, 0)](Reshape{3}.0, InplaceDimShuffle{x,0,x}.0)
Toposort index: 98
Inputs types: [TensorType(float32, 3D), TensorType(float32, (True, False, True))]
Inputs shapes: [(13, 10, 15), (1, 15, 1)]
Inputs strides: [(600, 60, 4), (60, 4, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Reshape{2}(Elemwise{Add}[(0, 0)].0, TensorConstant{[-1 15]}), Elemwise{Composite{((i0 + i1 + i2
+ i3) * scalar_sigmoid(i4) * (i5 - scalar_sigmoid(i4)))}}[(0, 0)](Reshape{3}.0, Reshape{3}.0, Reshape{3}.0, Reshape
{3}.0, Elemwise{Add}[(0, 0)].0, TensorConstant{(1, 1, 1) of 1.0})]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created.
This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizati
ons can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
I am unable to understand the error as to why the input shape would be (1,15,1) in the error and what are the 2 inputs which theano mentions?
The theano version I use is 0.9.0 and keras version is 2.0.4. If I rather use no features(F), the code runs smoothly.
Edit 1: batch size is 13, just for clarity in error log. Removing it also gives the exact same error.
I have a problem. I want to make 3D convolutional U-net. For this purpose I'm using Keras.
My data are MRI images from Data Science Bowl 2017 Competition. All MRI's were saved in numpy arrays (all pixels are scaled from 0 to 1) with shape:
data_ch.shape
(94, 50, 50, 50, 1)
94 - patients, 50 MRI slices of 50x50 images, 1 channel:
I want to make 3D Convolutional U-net, so the inputs and outputs of this net are same 3d arrays.
The 3D U-net:
input_img= Input(shape=(data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4]))
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(input_img)
x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)
x=UpSampling3D(size=(2, 2, 2))(x)
x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!
x=UpSampling3D(size=(2, 2, 2))(x)
x=Conv3D(filters=1, kernel_size=(3, 3, 3), activation='sigmoid')(x)
model=Model(input_img, x)
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.summary()
Layer (type) Output Shape Param #
=================================================================
input_5 (InputLayer) (None, 50, 50, 50, 1) 0
_________________________________________________________________
conv3d_27 (Conv3D) (None, 50, 50, 50, 8) 224
_________________________________________________________________
max_pooling3d_12 (MaxPooling (None, 25, 25, 25, 8) 0
_________________________________________________________________
conv3d_28 (Conv3D) (None, 25, 25, 25, 8) 1736
_________________________________________________________________
max_pooling3d_13 (MaxPooling (None, 13, 13, 13, 8) 0
_________________________________________________________________
up_sampling3d_12 (UpSampling (None, 26, 26, 26, 8) 0
_________________________________________________________________
conv3d_29 (Conv3D) (None, 26, 26, 26, 8) 1736
_________________________________________________________________
up_sampling3d_13 (UpSampling (None, 52, 52, 52, 8) 0
_________________________________________________________________
conv3d_30 (Conv3D) (None, 50, 50, 50, 1) 217
=================================================================
Total params: 3,913
Trainable params: 3,913
Non-trainable params: 0
But, when I attempted to fit data to this net:
model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)
the program displayed an error:
ValueError Traceback (most recent call last)
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
<ipython-input-26-b334d38d9608> in <module>()
----> 1 model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
1496 val_f=val_f, val_ins=val_ins, shuffle=shuffle,
1497 callback_metrics=callback_metrics,
-> 1498 initial_epoch=initial_epoch)
1499
1500 def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
1150 batch_logs['size'] = len(batch_ids)
1151 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1152 outs = f(ins_batch)
1153 if not isinstance(outs, list):
1154 outs = [outs]
C:\Users\Taranov\Anaconda3\lib\site-packages\keras\backend\theano_backend.py in __call__(self, inputs)
1156 def __call__(self, inputs):
1157 assert isinstance(inputs, (list, tuple))
-> 1158 return self.function(*inputs)
1159
1160
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
896 node=self.fn.nodes[self.fn.position_of_error],
897 thunk=thunk,
--> 898 storage_map=getattr(self.fn, 'storage_map', None))
899 else:
900 # old-style linkers raise their own exceptions
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\gof\link.py in raise_with_op(node, thunk, exc_info, storage_map)
323 # extra long error message in that case.
324 pass
--> 325 reraise(exc_type, exc_value, exc_trace)
326
327
C:\Users\Taranov\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb)
683 value = tp()
684 if value.__traceback__ is not tb:
--> 685 raise value.with_traceback(tb)
686 raise value
687
C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs)
882 try:
883 outputs =\
--> 884 self.fn() if output_subset is None else\
885 self.fn(output_subset=output_subset)
886 except Exception:
ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14
Apply node that caused the error: GpuAlloc(GpuDimShuffle{0,2,x,3,4,1}.0, Shape_i{0}.0, TensorConstant{13}, TensorConstant{2}, TensorConstant{13}, TensorConstant{13}, TensorConstant{8})
Toposort index: 163
Inputs types: [CudaNdarrayType(float32, (False, False, True, False, False, False)), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int8, scalar), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int64, scalar)]
Inputs shapes: [(10, 14, 1, 14, 14, 8), (), (), (), (), (), ()]
Inputs strides: [(21952, 196, 0, 14, 1, 2744), (), (), (), (), (), ()]
Inputs values: ['not shown', array(10, dtype=int64), array(13, dtype=int64), array(2, dtype=int8), array(13, dtype=int64), array(13, dtype=int64), array(8, dtype=int64)]
Outputs clients: [[GpuReshape{5}(GpuAlloc.0, MakeVector{dtype='int64'}.0)]]
HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.
I tried to follow recommendations and use theano flags:
import theano
import os
os.environ["THEANO_FLAGS"] = "mode=FAST_RUN,device=gpu,floatX=float32, optimizer='None',exception_verbosity=high"
But it still doesn't work.
Could you help me?
Many thanks!
Ok.... that sounds weird, but MaxPooling3D has some kind of bug with padding='same'. So I wrote your code without it, and added an initial padding just to make your dimensions compatible:
import keras.backend as K
inputShape = (data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4])
paddedShape = (data_ch.shape[1]+2, data_ch.shape[2]+2, data_ch.shape[3]+2, data_ch.shape[4])
#initial padding
input_img= Input(shape=inputShape)
x = Lambda(lambda x: K.spatial_3d_padding(x, padding=((1, 1), (1, 1), (1, 1))),
output_shape=paddedShape)(input_img) #Lambda layers require output_shape
#your original code without padding for MaxPooling layers (replace input_img with x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=2)(x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)
x=MaxPooling3D(pool_size=2)(x)
x=UpSampling3D(size=2)(x)
x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!
x=UpSampling3D(size=2)(x)
x=Conv3D(filters=1, kernel_size=3, activation='sigmoid')(x)
model=Model(input_img, x)
model.compile(optimizer='adadelta', loss='binary_crossentropy')
model.summary()
print(model.predict(data_ch)[1])
model.fit(data_ch,data_ch,epochs=1,verbose=2,batch_size=10)
Try reducing the batch size to something like 2, and if you see, your network needs more GPU, So try upgrading that as well.
In NVIDIA's paper "End to End Learning for Self-Driving Cars" there's an illustration showing the activation of first-layer feature maps:
I'm trying to recreate this with the Comma AI model, but the only visualisation tools I've found are Keras' instructions for gradient ascent and descent, rather than simply viewing activations. what should I be looking for?
EDIT IN RESPONSE TO COMMENT
I tried implementing the code in this answer using the below code:
from keras import backend as K
import json
from keras.models import model_from_json
with open('outputs/steering_model/steering_angle.json', 'r') as jfile:
z = json.load(jfile)
model = model_from_json(z)
print("Loaded model")
model.load_weights('outputs/steering_model/steering_angle.keras')
print("Loaded weights")
img_width = 320
img_height = 160
outputs = [layer.output for layer in model.layers] # all layer outputs
functors = [K.function([inp]+ [K.learning_phase()], [out]) for out in outputs] # evaluation functions
# Testing
test = np.random.random((1, 3, img_width, img_height))
layer_outs = [func([test, 1.]) for func in functors]
print layer_outs
This give the following output error:
Using Theano backend.
Loaded model
Loaded weights
Traceback (most recent call last):
File "vis-layers.py", line 22, in <module>
layer_outs = [func([test, 1.]) for func in functors]
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 959, in __call__
return self.function(*inputs)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py", line 871, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/gof/link.py", line 314, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py", line 859, in __call__
outputs = self.fn()
ValueError: Shape mismatch: x has 49152 cols (and 1 rows) but y has 12800 rows (and 512 cols)
Apply node that caused the error: Dot22(Elemwise{Composite{Switch(GT(i0, i1), i0, expm1(i0))}}[(0, 0)].0, dense_1_W)
Toposort index: 50
Inputs types: [TensorType(float32, matrix), TensorType(float32, matrix)]
Inputs shapes: [(1, 49152), (12800, 512)]
Inputs strides: [(196608, 4), (2048, 4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Elemwise{Add}[(0, 0)](Dot22.0, InplaceDimShuffle{x,0}.0)]]
I thought this might be a problem with th vs tf dimensions, so tried changing the test input to:
test = np.random.random((1, img_height, img_width, 3))
which gave the following error:
Using Theano backend.
Loaded model
Loaded weights
Traceback (most recent call last):
File "vis-layers.py", line 22, in <module>
layer_outs = [func([test, 1.]) for func in functors]
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 959, in __call__
return self.function(*inputs)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py", line 871, in __call__
storage_map=getattr(self.fn, 'storage_map', None))
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/gof/link.py", line 314, in raise_with_op
reraise(exc_type, exc_value, exc_trace)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/theano/compile/function_module.py", line 859, in __call__
outputs = self.fn()
ValueError: CorrMM images and kernel must have the same stack size
Apply node that caused the error: CorrMM{half, (4, 4)}(Elemwise{Composite{(i0 + (i1 * i2))}}.0, Subtensor{::, ::, ::int64, ::int64}.0)
Toposort index: 9
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(1, 320, 160, 3), (16, 3, 8, 8)]
Inputs strides: [(2250000, 6000, 12, 4), (768, 256, -32, -4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Subtensor{int64:int64:int8, int64:int64:int8, int64:int64:int8, int64:int64:int8}(CorrMM{half, (4, 4)}.0, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, Constant{0}, Constant{16}, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1})]]
Backtrace when the node is created(use Theano flag traceback.limit=N to make it longer):
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/utils/layer_utils.py", line 43, in layer_from_config
return layer_class.from_config(config['config'])
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/models.py", line 1091, in from_config
model.add(layer)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/models.py", line 332, in add
output_tensor = layer(self.outputs[0])
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 572, in __call__
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 635, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/engine/topology.py", line 166, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/layers/convolutional.py", line 475, in call
filter_shape=self.W_shape)
File "/home/ubuntu/anaconda2/lib/python2.7/site-packages/keras/backend/theano_backend.py", line 1508, in conv2d
filter_shape=filter_shape)
EDIT: Output of model.summary()
____________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
====================================================================================================
lambda_1 (Lambda) (None, 3, 160, 320) 0 lambda_input_1[0][0]
____________________________________________________________________________________________________
convolution2d_1 (Convolution2D) (None, 16, 40, 80) 3088 lambda_1[0][0]
____________________________________________________________________________________________________
elu_1 (ELU) (None, 16, 40, 80) 0 convolution2d_1[0][0]
____________________________________________________________________________________________________
convolution2d_2 (Convolution2D) (None, 32, 20, 40) 12832 elu_1[0][0]
____________________________________________________________________________________________________
elu_2 (ELU) (None, 32, 20, 40) 0 convolution2d_2[0][0]
____________________________________________________________________________________________________
convolution2d_3 (Convolution2D) (None, 64, 10, 20) 51264 elu_2[0][0]
____________________________________________________________________________________________________
flatten_1 (Flatten) (None, 12800) 0 convolution2d_3[0][0]
____________________________________________________________________________________________________
dropout_1 (Dropout) (None, 12800) 0 flatten_1[0][0]
____________________________________________________________________________________________________
elu_3 (ELU) (None, 12800) 0 dropout_1[0][0]
____________________________________________________________________________________________________
dense_1 (Dense) (None, 512) 6554112 elu_3[0][0]
____________________________________________________________________________________________________
dropout_2 (Dropout) (None, 512) 0 dense_1[0][0]
____________________________________________________________________________________________________
elu_4 (ELU) (None, 512) 0 dropout_2[0][0]
____________________________________________________________________________________________________
dense_2 (Dense) (None, 1) 513 elu_4[0][0]
====================================================================================================
Total params: 6,621,809
Trainable params: 6,621,809
Non-trainable params: 0
____________________________________________________________________________________________________
EDIT: DEBUGGING WITH SINGLE LAYER
In order to debug the issue with input shapes, I rewrote the script for a single layer:
from keras import backend as K
import numpy as np
import json
from keras.models import model_from_json
with open('outputs/steering_model/steering_angle.json', 'r') as jfile:
z = json.load(jfile)
model = model_from_json(z)
print("Loaded model")
model.load_weights('outputs/steering_model/steering_angle.keras')
print("Loaded weights")
layer_name = 'lambda_1'
img_width = 160
img_height = 320
inp = model.input
layer_idx = [idx for idx, layer in enumerate(model.layers) if layer.name == layer_name][0]
output = model.layers[layer_idx].output
functor = K.function([inp]+ [K.learning_phase()], output) # evaluation function
# Testing
test = np.random.random((1, img_height, img_width, 3))
layer_out = functor([test, 1.])
print layer_out
The output from this is as follows:
Using Theano backend.
Loaded model
Loaded weights
[[[[-0.99223709 -0.99468529 -0.99318016]
[-0.99725926 -0.9924705 -0.9994905 ]
[-0.99380279 -0.99291307 -0.99927235]
...,
[-0.99361622 -0.99258155 -0.99954134]
[-0.99748689 -0.99217939 -0.99918425]
[-0.99475586 -0.99366009 -0.992827 ]]
[[-0.99330682 -0.99756712 -0.99795902]
[-0.99421203 -0.99240923 -0.99438184]
[-0.99222761 -0.99425066 -0.99886942]
...,
[-0.99329156 -0.99460274 -0.99994165]
[-0.99763876 -0.99870259 -0.9998613 ]
[-0.99962425 -0.99702215 -0.9943046 ]]
[[-0.99947125 -0.99577188 -0.99294066]
[-0.99582225 -0.99568367 -0.99345332]
[-0.99823713 -0.99376178 -0.99432898]
...,
[-0.99828976 -0.99264622 -0.99669623]
[-0.99485278 -0.99353015 -0.99411404]
[-0.99832171 -0.99390954 -0.99620205]]
...,
[[-0.9980613 -0.99474132 -0.99680966]
[-0.99378282 -0.99288809 -0.99248403]
[-0.99375945 -0.9966079 -0.99440354]
...,
[-0.99634677 -0.99931824 -0.99611002]
[-0.99781156 -0.99990571 -0.99249381]
[-0.9996115 -0.99991143 -0.99486816]]
[[-0.99839222 -0.99690026 -0.99410695]
[-0.99551272 -0.99262673 -0.99934679]
[-0.99432331 -0.99822938 -0.99294668]
...,
[-0.99515969 -0.99867356 -0.9926796 ]
[-0.99478716 -0.99883151 -0.99760127]
[-0.9982425 -0.99547088 -0.99658638]]
[[-0.99240851 -0.99792403 -0.99360847]
[-0.99226022 -0.99546915 -0.99411654]
[-0.99558711 -0.9960795 -0.9993062 ]
...,
[-0.99745959 -0.99276334 -0.99800634]
[-0.99249429 -0.99748743 -0.99576926]
[-0.99531293 -0.99618822 -0.99997312]]]]
However, attempting the same on the first convolutional layer (convolution2d_1) with an 80x40 image returns the same error:
ValueError: CorrMM images and kernel must have the same stack size
Apply node that caused the error: CorrMM{half, (4, 4)}(Elemwise{Composite{(i0 + (i1 * i2))}}.0, Subtensor{::, ::, ::int64, ::int64}.0)
Toposort index: 9
Inputs types: [TensorType(float32, 4D), TensorType(float32, 4D)]
Inputs shapes: [(1, 40, 80, 3), (16, 3, 8, 8)]
Inputs strides: [(38400, 960, 12, 4), (768, 256, -32, -4)]
Inputs values: ['not shown', 'not shown']
Outputs clients: [[Subtensor{int64:int64:int8, int64:int64:int8, int64:int64:int8, int64:int64:int8}(CorrMM{half, (4, 4)}.0, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, Constant{0}, Constant{16}, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1}, ScalarFromTensor.0, ScalarFromTensor.0, Constant{1})]]
EDIT: OUTPUT LAYER DATA AS IMAGE
The following code replaces the random image with a loaded one, and takes the layer output and saves it as an image:
input_img_data = imread(impath+'.png').astype(np.float32)
# change image to 4d theano array
test = np.expand_dims(input_img_data,axis=0)
print test.shape
layer_out = functor([test, 1.])
img = Image.fromarray(layer_out[0,:,:,:], 'RGB')
img.save('activ_%s_%s.png' % (layer_name,impath))
print("Created Image")
Here is the final code that does what I want it to do, still rough and in need of tidying up:
from keras import backend as K
from PIL import Image
from scipy.misc import imread
from scipy.misc import imsave
import numpy as np
import json
from keras.models import model_from_json
with open('outputs/steering_model/steering_angle.json', 'r') as jfile:
z = json.load(jfile)
model = model_from_json(z)
print("Loaded model")
model.load_weights('outputs/steering_model/steering_angle.keras')
print("Loaded weights")
layer_name = 'lambda_1'
#layer_name = 'convolution2d_1'
#layer_name = 'elu_1'
#layer_name = 'convolution2d_2'
impaths = ['track','road','mway']
img_width = 500
img_height = 375
inp = model.input
layer_idx = [idx for idx, layer in enumerate(model.layers) if layer.name == layer_name][0]
output = model.layers[layer_idx].output
functor = K.function([inp]+ [K.learning_phase()], output) # evaluation function
for impath in impaths:
input_img_data = imread('testimages/'+impath+'.png').astype(np.float32)
input_img_data = np.rollaxis(input_img_data,2,0) # change to (channels,h,w)
test = np.expand_dims(input_img_data,axis=0) # change to (dims,channels,h,w)
print("Test Shape: %s" % (test.shape,)) # check shape
layer_out = functor([test, 1.])
print ("Output Shape: %s" % (layer_out.shape,)) # check output shape
# save multiple greyscale images
layer_out = np.rollaxis(layer_out,0,4)
print ("Output Image Shape: %s" % (layer_out.shape,)) # check output shape
count = 1
for x in layer_out:
x = np.rollaxis(x,2,0)
print ("Final Image Shape: %s" % (x.shape,)) # check output shape
imsave('activationimages/activ_%s_%s_%d.png' % (layer_name,impath,count),x[0,:,:])
count = count + 1
The main issue was wrangling the shapes of the various input and output layers - hence all the print commands in the above code, for debugging.
A second confusion was that I was interpreting an array shape of (3,w,h) as a single RGB (3-channel) image, rather than one greyscale image.
The version above tests an array of images at a time (hardcoded image path). The lambda_1 level outputs a single RGB image per test image, convolution2d_1 and elu_1 output sixteen smaller (25%) greyscale images - one for each filter. And, I hope, so on.
I will add a Github link to a tidied gist with image stitching when I've done this. I've learned a lot.