I am trying to enforce a structural prior on the two outputs of my network.
The network has two heads and each predicts a different quantity: f_1(x) and f_2(x) (and each branch has its own separate loss function).
I am basically trying to add a third loss that is a function of only the outputs: L(f_1(x),f_2(x)).
I know this can easily be done if I had a custom TF loop, but any idea how to accomplish this in Keras? (I am using tf.dataset to feed the input data).
Thank you
Related
I am trying to convert my CNN written with tensorflow layers to use the keras api in tensorflow (I am using the keras api provided by TF 1.x), and am having issue writing a custom loss function, to train the model.
According to this guide, when defining a loss function it expects the arguments (y_true, y_pred)
https://www.tensorflow.org/guide/keras/train_and_evaluate#custom_losses
def basic_loss_function(y_true, y_pred):
return ...
However, in every example I have seen, y_true is somehow directly related to the model (in the simple case it is the output of the network). In my problem, this is not the case. How do implement this if my loss function depends on some training data that is unrelated to the tensors of the model?
To be concrete, here is my problem:
I am trying to learn an image embedding trained on pairs of images. My training data includes image pairs and annotations of matching points between the image pairs (image coordinates). The input feature is only the image pairs, and the network is trained in a siamese configuration.
I am able to implement this successfully with tensorflow layers and train it sucesfully with tensorflow estimators.
My current implementations builds a tf Dataset from a large database of tf Records, where the features is a dictionary containing the images and arrays of matching points. Before I could easily feed these arrays of image coordinates to the loss function, but here it is unclear how to do so.
There is a hack I often use that is to calculate the loss within the model, by means of Lambda layers. (When the loss is independent from the true data, for instance, and the model doesn't really have an output to be compared)
In a functional API model:
def loss_calc(x):
loss_input_1, loss_input_2 = x #arbirtray inputs, you choose
#according to what you gave to the Lambda layer
#here you use some external data that doesn't relate to the samples
externalData = K.constant(external_numpy_data)
#calculate the loss
return the loss
Using the outputs of the model itself (the tensor(s) that are used in your loss)
loss = Lambda(loss_calc)([model_output_1, model_output_2])
Create the model outputting the loss instead of the outputs:
model = Model(inputs, loss)
Create a dummy keras loss function for compilation:
def dummy_loss(y_true, y_pred):
return y_pred #where y_pred is the loss itself, the output of the model above
model.compile(loss = dummy_loss, ....)
Use any dummy array correctly sized regarding number of samples for training, it will be ignored:
model.fit(your_inputs, np.zeros((number_of_samples,)), ...)
Another way of doing it, is using a custom training loop.
This is much more work, though.
Although you're using TF1, you can still turn eager execution on at the very beginning of your code and do stuff like it's done in TF2. (tf.enable_eager_execution())
Follow the tutorial for custom training loops: https://www.tensorflow.org/tutorials/customization/custom_training_walkthrough
Here, you calculate the gradients yourself, of any result regarding whatever you want. This means you don't need to follow Keras standards of training.
Finally, you can use the approach you suggested of model.add_loss.
In this case, you calculate the loss exaclty the same way I did in the first answer. And pass this loss tensor to add_loss.
You can probably compile a model with loss=None then (not sure), because you're going to use other losses, not the standard one.
In this case, your model's output will probably be None too, and you should fit with y=None.
my problem is the following:
I am working on an object detection problem and would like to use dropout during test time to obtain a distribution of outputs. The object detection network consists of a training model and a prediction model, which wraps around the training model. I would like to perform several stochastic forward passes using the training model and combine these e.g. by averaging the predictions in the prediction wrapper. Is there a way of doing this in a keras model instead of requiring an intermediate processing step using numpy?
Note that this question is not about how to enable dropout during test time
def prediction_wrapper(model):
# Example code.
# Arguments
# model: the training model
regression = model.outputs[0]
classification = model.outputs[1]
predictions = # TODO: perform several stochastic forward passes (dropout during train and test time) here
avg_predictions = # TODO: combine predictions here, e.g. by computing the mean
outputs = # TODO: do some processing on avg_predictions
return keras.models.Model(inputs=model.inputs, outputs=outputs, name=name)
I use keras with a tensorflow backend.
I appreciate any help!
The way I understand, you're trying to average the weight updates for a single sample while Dropout is enabled. Since dropout is random, you would get different weight updates for the same sample.
If this understanding is correct, then you could create a batch by duplicating the same sample. Here I am assuming that the Dropout is different for each sample in a batch. Since, backpropagation averages the weight updates anyway, you would get your desired behavior.
If that does not work, then you could write a custom loss function and train with a batch-size of one. You could update a global counter inside your custom loss function and return non-zero loss only when you've averaged them the way you want it. I don't know if this would work, it's just an idea.
I have an input pipeline where samples are generated on fly. I use keras and custom ImageDataGenerator and corresponding Iterator to get samples in memory.
Under assumption that keras in my setup is using feed_dict (and that assumption is a question to me) I am thinking of speeding things up by switching to raw tensorflow + Dataset.from_generator().
Here I see that suggested solution for input pipelines that generate data on fly in the most recent Tensorflow is to use Dataset.from_generator().
Questions:
Does keras with Tensorflow backend use feed_dict method?
If I switch to raw tensorflow + Dataset.from_generator(my_sample_generator) will that cut feed_dict memory copy overhead and buy me performance?
During predict (evaluation) phase apart from batch_x, batch_y I have also opaque index vector from my generator output. That vector corresponds to sample ids in the batch_x. Does that mean that I'm stuck with feed_dict approach for predict phase because I need that extra batch_z output from iterator?
The new tf.contrib.data.Dataset.from_generator() can potentially speed up your input pipeline by overlapping the data preparation with training. However, you will tend to get the best performance by switching over to TensorFlow ops in your input pipeline wherever possible.
To answer your specific questions:
The Keras TensorFlow backend uses tf.placeholder() to represent compiled function inputs, and feed_dict to pass arguments to a function.
With the recent optimizations to tf.py_func() and feed_dict copy overhead, I suspect the amount of time spent in memcpy() will be the same. However, you can more easily use Dataset.from_generator() with Dataset.prefetch() to overlap the training on one batch with preprocessing on the next batch.
It sounds like you can define a separate iterator for the prediction phase. The tf.estimator.Estimator class does something similar by instantiating different "input functions" with different signatures for training and evaluation, then building a separate graph for each role.
Alternatively, you could add a dummy output to your training iterator (for the batch_z values) and switch between training and evaluation iterators using a "feedable iterator".
What is the difference between losses/clone_0/softmax_cross_entropy_loss and losses/clone_0/aux_loss/value in inception-v4?
Currently, I'm training a large-scale model using tf-slim and inception-v4 network on 4 GPUs(--num_clones=4 ). but these two charts are completely different. after 190K steps with batch-size=128, I get these charts:Losses
as you can see in the image total loss and have a similar trend. but the softmax_cross_entropy have a completely different procedure!
Which one of these losses can describe the training procedure better?
You should use the first, main one. You can read about the auxiliary head and its loss in here Does the Inception Model have two softmax outputs?
This aux_loss is defined here: https://github.com/tensorflow/models/blob/4bd29ac0ba1004d7393b7d029b05257dffd5cbe6/inception/inception/inception_model.py#L135
There are quite a few examples on how to use LSTMs alone in TF, but I couldn't find any good examples on how to train CNN + LSTM jointly.
From what I see, it is not quite straightforward how to do such training, and I can think of a few options here:
First, I believe the simplest solution (or the most primitive one) would be to train CNN independently to learn features and then to train LSTM on CNN features without updating the CNN part, since one would probably have to extract and save these features in numpy and then feed them to LSTM in TF. But in that scenario, one would probably have to use a differently labeled dataset for pretraining of CNN, which eliminates the advantage of end to end training, i.e. learning of features for final objective targeted by LSTM (besides the fact that one has to have these additional labels in the first place).
Second option would be to concatenate all time slices in the batch
dimension (4-d Tensor), feed it to CNN then somehow repack those
features to 5-d Tensor again needed for training LSTM and then apply a cost function. My main concern, is if it is possible to do such thing. Also, handling variable length sequences becomes a little bit tricky. For example, in prediction scenario you would only feed single frame at the time. Thus, I would be really happy to see some examples if that is the right way of doing joint training. Besides that, this solution looks more like a hack, thus, if there is a better way to do so, it would be great if someone could share it.
Thank you in advance !
For joint training, you can consider using tf.map_fn as described in the documentation https://www.tensorflow.org/api_docs/python/tf/map_fn.
Lets assume that the CNN is built along similar lines as described here https://github.com/tensorflow/models/blob/master/tutorials/image/cifar10/cifar10.py.
def joint_inference(sequence):
inference_fn = lambda image: inference(image)
logit_sequence = tf.map_fn(inference_fn, sequence, dtype=tf.float32, swap_memory=True)
lstm_cell = tf.contrib.rnn.LSTMCell(128)
output_state, intermediate_state = tf.nn.dynamic_rnn(cell=lstm_cell, inputs=logit_sequence)
projection_function = lambda state: tf.contrib.layers.linear(state, num_outputs=num_classes, activation_fn=tf.nn.sigmoid)
projection_logits = tf.map_fn(projection_function, output_state)
return projection_logits
Warning: You might have to look into device placement as described here https://www.tensorflow.org/tutorials/using_gpu if your model is larger than the memory gpu can allocate.
An Alternative would be to flatten the video batch to create an image batch, do a forward pass from CNN and reshape the features for LSTM.