The following code (based on https://keras.io/getting-started/faq/#how-can-i-obtain-the-output-of-an-intermediate-layer) allows us to print the output of an intermediate layer of a model, given some input, which we need to provide. Specifically, in this example, I am printing the output of the layer dense, given the input to the layer input_1, which also happens to be the input layer of my model (but this does not have to be like that).
import numpy as np
import tensorflow as tf
def get_model():
inp = tf.keras.layers.Input(shape=(1,))
x = tf.keras.layers.Dense(8)(inp)
x = tf.keras.layers.Dense(16)(x)
out = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs=inp, outputs=out)
model.summary()
return model
def train():
my_model = get_model()
my_model.compile(optimizer="adam", loss="mse")
get_layer_output = tf.keras.backend.function([my_model.get_layer("input_1").input],
[my_model.get_layer("dense").output])
data_x = np.array([[1], [2], [3], [4]])
layer_output = get_layer_output(data_x)[0]
print(layer_output)
if __name__ == '__main__':
train()
However, I would like to print the output of each layer, given the output of the corresponding previous layer (as defined by the model), while training the model, i.e. after each mini-batch. I tried to use a callback, which calls tf.print for printing the output of a model, but I am getting an error, which is described in this Github issue (i.e. there is a bug in TensorFlow 2.0, which is the version I am using and that I want to use).
To be clearer, I would like to debug the output of each layer while I am training the model, so that I can understand how the inputs flow throughout each layer and if the activations are not too high (explode) or too small (vanish). I could iteratively provide a batch of data to get_layer_output, but I would like to be able to print the activations of each layer while training the model with fit or fit_generator. Furthermore, I would like to understand how the values of the activations evolve from the input layer to the output layer and not just print the activations of one layer given the input to another layer.
Here's a Github issue that asks a similar thing.
Related
Current simple model:
from tensorflow.keras import Model
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Input
from tensorflow.keras.optimizers import Adam
def model():
input_A = Input(shape=(6, ))
out = Dense(64, activation="relu")(input_A)
out = Dense(32, activation="relu")(out)
outputs = Dense(1, activation="tanh")(out)
model = Model(
inputs=input_A,
outputs=outputs,
name="switchable_inputs_model")
model.compile(loss="mse", optimizer=Adam(), metrics=["accuracy"])
return model
I want to have another input layer input_B which will not be active all the time during learning. Let us say we have two input layers: input A, input B. However, at a given time, only one input layer can be active. This selection of input layer is decided by a binary combination of information available at the execution time(learning stage). For instance, if it is 1 0, then input layer A will be used. Similarly, if it is 0 1, input layer B will be used.
How can I do this?
It's hard to guess from your question what you are trying to accomplish in detail, but you should carefully consider if that is necessary.
It's common practice to have an input layer of a fixed size that matches the structure of your data. You preprocess your data to match that shape.
In the domain of e.g. images this might mean:
If you have images of different resolutions, you could consider cropping, padding or resizing your inputs to a fixed size.
If there is a rationale behind this please clarify.
I have defined my Functional model like this:
base_model = VGG16(include_top=False, input_shape=(224,224,3), pooling='avg')
inputs = tf.keras.Input(shape=(224,224,3))
x = preprocess_input(inputs)
x = base_model(x, training=False)
x = tf.keras.layers.Dropout(0.2)(x, training=True)
outputs = tf.keras.layers.Dense(1, activation='sigmoid')(x)
model = tf.keras.Model(inputs=inputs, outputs=outputs)
The problem is when I call .evaluate() or .predict() I get slightly different results everytime when using the exact same batch (with shuffle=False in my dataset, and all the random seeds initialized).
I tried reconstructing the model without some of the layers and I found the culprit to be these 2 layers constructed by the line x=preprocess_input(inputs), which give randomness to the results:
model summary
Note: preprocess_input is a vgg16 preprocessing function at tf.keras.applications.vgg16.preprocess_input.
However, if I redefine my Functional model as Sequential:
new_model = tf.keras.Sequential()
new_model.add(model.layers[0]) #input layer
new_model.add(tf.keras.layers.Lambda(preprocess_input))
new_model.add(model.layers[3]) #vgg16
new_model.add(model.layers[4]) #dropout
new_model.add(model.layers[5]) #dense
The problem is gone and I get consistent results from .evaluate() or .predict().
What could potentially cause the Functional model to behave like this?
EDIT
As xdurch0 pointed out, it was the dropout layer at fault for different results. The functional model applied dropout during .predict() and .evaluate() methods.
I'm training a language model in Keras and would like to speed up training by using sampled softmax as the final activation function in my network. From the TF docs, it looks like I need to supply arguments for weights and biases, but I'm unsure of what is expected as input for these. It seems like I could write a custom function in Keras as follows:
import keras.backend as K
def sampled_softmax(weights, biases, y_true, y_pred, num_sampled, num_classes):
return K.sampled_softmax(weights, biases, y_true, y_pred, num_sampled, num_classes)
However, I'm unsure of how to "plug this in" to my existing network. The architecture for the LM is pretty dead-simple:
model = Sequential()
model.add(Embedding(input_dim=len(vocab), output_dim=256))
model.add(LSTM(1024, return_sequence=True))
model.add(Dense(output_dim=len(vocab), activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')
Given this architecture, could I pass the sampled_softmax function as the loss argument when calling the compile method on the model? Or do this need to be written as a layer that comes after the final fully-connected layer. Any guidance here would be greatly appreciated. Thanks.
The key observation here is that the TensorFlow sampled softmax function returns actual losses, not a set of predictions over the set of possible labels to compare with the ground truth data to then compute losses as a separate step. This makes the model setup a little bit weird.
First, we add a second input layer to the model that encodes the target (training) data a second time as an input, in addition to being the target output. This is used for the labels argument of the sampled_softmax_loss function. It needs to be a Keras input, because it's treated as an input when we go to instantiate and set up the model.
Second, we construct a new custom Keras layer that calls the sampled_softmax_loss function with two Keras layers as its inputs: the output of the dense layer that predicts our classes, and then the second input that contains a copy of the training data. Note that we're doing some serious hackery accessing the _keras_history instance variable to fetch the weight and bias tensors from the output tensor of the original fully-connected layer.
Finally, we have to construct a new "dumb" loss function that ignores the training data and just uses the loss reported by the sampled_softmax_loss function.
Note that because the sampled softmax function returns losses, not class predictions, you can't use this model specification for validation or inference. You'll need to re-use the trained layers from this "training version" in a new specification that applies a standard softmax function to the original dense layer which has the default activation function applied.
There is definitely a more elegant way to do this, but I believe this works, so I figured I'd post it here now as-is rather than wait until I have something that's a little bit neater. For example, you'd probably want to make the number of classes an argument of the SampledSoftmax layer, or better yet, condense this all into the loss function as in the original question and avoid passing in the training data twice.
from keras.models import Model
from keras.layers import Input, Dense, Layer
from keras import backend as K
class SampledSoftmax(Layer):
def __init__(self, **kwargs):
super(SampledSoftmax, self).__init__(**kwargs)
def call(self, inputs):
"""
The first input should be the model as it were, and the second the
target (i.e., a repeat of the training data) to compute the labels
argument
"""
# the labels input to this function is batch size by 1, where the
# value at position (i, 1) is the index that is true (not zero)
# e.g., (0, 0, 1) => (2) or (0, 1, 0, 0) => (1)
return K.tf.nn.sampled_softmax_loss(weights=inputs[0]._keras_history[0].weights[0],
biases=inputs[0]._keras_history[0].bias,
inputs=inputs[0],
labels=K.tf.reshape(K.tf.argmax(inputs[1], 1), [-1, 1]),
num_sampled=1000,
num_classes=200000)
def custom_loss(y_true, y_pred):
return K.tf.reduce_mean(y_pred)
num_classes = 200000
input = Input(shape=(300,))
target_input = Input(shape=(num_classes,))
dense = Dense(num_classes)
outputs = dense(input)
outputs = SampledSoftmax()([outputs, target_input])
model = Model([input, target_input], outputs)
model.compile(optimizer=u'adam', loss=custom_loss)
# train as desired
Following the upgrade to Keras 2.0.9, I have been using the multi_gpu_model utility but I can't save my models or best weights using
model.save('path')
The error I get is
TypeError: can’t pickle module objects
I suspect there is some problem gaining access to the model object. Is there a work around this issue?
To be honest, the easiest approach to this is to actually examine the multi gpu parallel model using
parallel_model.summary()
(The parallel model is simply the model after applying the multi_gpu function). This clearly highlights the actual model (in I think the penultimate layer - I am not at my computer right now). Then you can use the name of this layer to save the model.
model = parallel_model.get_layer('sequential_1)
Often its called sequential_1 but if you are using a published architecture, it may be 'googlenet' or 'alexnet'. You will see the name of the layer from the summary.
Then its simple to just save
model.save()
Maxims approach works, but its overkill I think.
Rem: you will need to compile both the model, and the parallel model.
Workaround
Here's a patched version that doesn't fail while saving:
from keras.layers import Lambda, concatenate
from keras import Model
import tensorflow as tf
def multi_gpu_model(model, gpus):
if isinstance(gpus, (list, tuple)):
num_gpus = len(gpus)
target_gpu_ids = gpus
else:
num_gpus = gpus
target_gpu_ids = range(num_gpus)
def get_slice(data, i, parts):
shape = tf.shape(data)
batch_size = shape[:1]
input_shape = shape[1:]
step = batch_size // parts
if i == num_gpus - 1:
size = batch_size - step * i
else:
size = step
size = tf.concat([size, input_shape], axis=0)
stride = tf.concat([step, input_shape * 0], axis=0)
start = stride * i
return tf.slice(data, start, size)
all_outputs = []
for i in range(len(model.outputs)):
all_outputs.append([])
# Place a copy of the model on each GPU,
# each getting a slice of the inputs.
for i, gpu_id in enumerate(target_gpu_ids):
with tf.device('/gpu:%d' % gpu_id):
with tf.name_scope('replica_%d' % gpu_id):
inputs = []
# Retrieve a slice of the input.
for x in model.inputs:
input_shape = tuple(x.get_shape().as_list())[1:]
slice_i = Lambda(get_slice,
output_shape=input_shape,
arguments={'i': i,
'parts': num_gpus})(x)
inputs.append(slice_i)
# Apply model on slice
# (creating a model replica on the target device).
outputs = model(inputs)
if not isinstance(outputs, list):
outputs = [outputs]
# Save the outputs for merging back together later.
for o in range(len(outputs)):
all_outputs[o].append(outputs[o])
# Merge outputs on CPU.
with tf.device('/cpu:0'):
merged = []
for name, outputs in zip(model.output_names, all_outputs):
merged.append(concatenate(outputs,
axis=0, name=name))
return Model(model.inputs, merged)
You can use this multi_gpu_model function, until the bug is fixed in keras. Also, when loading the model, it's important to provide the tensorflow module object:
model = load_model('multi_gpu_model.h5', {'tf': tf})
How it works
The problem is with import tensorflow line in the middle of multi_gpu_model:
def multi_gpu_model(model, gpus):
...
import tensorflow as tf
...
This creates a closure for the get_slice lambda function, which includes the number of gpus (that's ok) and tensorflow module (not ok). Model save tries to serialize all layers, including the ones that call get_slice and fails exactly because tf is in the closure.
The solution is to move import out of multi_gpu_model, so that tf becomes a global object, though still needed for get_slice to work. This fixes the problem of saving, but in loading one has to provide tf explicitly.
It's something that need a little work around by loading the multi_gpu_model weight to the regular model weight.
e.g.
#1, instantiate your base model on a cpu
with tf.device("/cpu:0"):
model = create_model()
#2, put your model to multiple gpus, say 2
multi_model = multi_gpu_model(model, 2)
#3, compile both models
model.compile(loss=your_loss, optimizer=your_optimizer(lr))
multi_model.compile(loss=your_loss, optimizer=your_optimizer(lr))
#4, train the multi gpu model
# multi_model.fit() or multi_model.fit_generator()
#5, save weights
model.set_weights(multi_model.get_weights())
model.save(filepath=filepath)
`
refrence: https://github.com/fchollet/keras/issues/8123
I recently have started using Keras to build neural networks. I built a simple CNN to classify MNIST dataset. Before learning the model I used K.set_image_dim_ordering('th') in order to plot a convolutional layer weights. Right now I am trying to visualize convolutional layer output with K.function method, but I keep getting error.
Here is what I want to do for now:
input_image = X_train[2:3,:,:,:]
output_layer = model.layers[1].output
input_layer = model.layers[0].input
output_fn = K.function(input_layer, output_layer)
output_image = output_fn.predict(input_image)
print(output_image.shape)
output_image = np.rollaxis(np.rollaxis(output_image, 3, 1), 3, 1)
print(output_image.shape)
fig = plt.figure()
for i in range(32):
ax = fig.add_subplot(4,8,i+1)
im = ax.imshow(output_image[0,:,:,i], cmap="Greys")
plt.xticks(np.array([]))
plt.yticks(np.array([]))
fig.subplots_adjust(right=0.8)
cbar_ax = fig.add_axes([1, 0.1, 0.05 ,0.8])
fig.colorbar(im, cax = cbar_ax)
plt.tight_layout()
plt.show()
And this is what I get:
File "/home/kinshiryuu/anaconda3/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1621, in function
return Function(inputs, outputs, updates=updates)
File "/home/kinshiryuu/anaconda3/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1569, in __init__
raise TypeError('`inputs` to a TensorFlow backend function '
TypeError: `inputs` to a TensorFlow backend function should be a list or tuple.
You should do the following changes:
output_fn = K.function([input_layer], [output_layer])
output_image = output_fn([input_image])
K.function takes the input and output tensors as list so that you can create a function from many input to many output. In your case one input to one output.. but you need to pass them as a list none the less.
Next K.function returns a tensor function and not a model object where you can use predict(). The correct way of using is just to call as a function
I think you can also use K.function to get gradients.
self.action_gradients = K.gradients(Q_values, actions)
self.get_action_gradients=K.function[*self.model.input, K.learning_phase()], outputs=action_gradients)
which basically runs the graph to obtain the Q-value to calculate the gradient of the Q-value w.r.t. action vector in DDPG. Source code here (lines 64 to 70): https://github.com/nyck33/autonomous_quadcopter/blob/master/criticSolution.py#L65
In light of the accepted answer and this usage here (originally from project 5 autonomous quadcopter in the Udacity Deep Learning nanodegree), a question remains in my mind, ie. is K.function() something that can be used fairly flexibly to run the graph and to designate as outputs of K.function() for example outputs of a particular layer, gradients or even weights themselves?
Lines 64 to 67 here: https://github.com/nyck33/autonomous_quadcopter/blob/master/actorSolution.py
It is being used as a custom training function for the actor network in DDPG:
#caller
self.actor_local.train_fn([states, action_gradients, 1])
#called
self.train_fn = K.function(inputs=[self.model.input, action_gradients, K.learning_phase()], \
outputs=[], updates=updates_op)
outputs is given a value of an empty list because we merely want to train the actor network with the action_gradients from the critic network.