I want to build a RNN with thousands of timesteps, so the proper way is to use the while_loop function since the GPU will be out of memory in for loops.
But I could not find a way to save rnn outputs in every step. I tried using a global list or using tf.concat() to accumulate the output. Neither worked. It seems like while_loop() can only be used to get the final output.
Is there any solution to get all the outputs?
Try tf.nn.dynamic_rnn which does exactly this using while_loop and TensorArray objects.
Related
I am trying to predict() the output for a single data point d, using my trained Keras model loaded from a file. But I get a ValueError If predicting from data tensors, you should specify the 'step' argument. What does that mean?
I tried setting step=1, but then I get a different error ValueError: Cannot feed value of shape () for Tensor u'input_1:0', which has shape '(?, 600)'.
Here is my code:
d = np.concatenate((hidden[p[i]], hidden[x[i]])).resize((1,600))
hidden[p[i]] = autoencoder.predict(d,steps=)
The model is expecting (?,600) as input. I have concatenated two numpy arrays of shape (300,) each to get (600,), which is resized to (1,600). This (1,600) is my input to predict().
In my case, the input to predict was None (because I had a bug in another part of the code).
In official doc, steps refer to the total number of steps before stopping. So steps=1 means make predictions on one batch instead of making prediction on one record (single data point).
https://keras.io/models/sequential/
-> Define value of steps argument,
d = np.concatenate((hidden[p[i]],
hidden[x[i]])).resize((1,600))
hidden[p[i]] = autoencoder.predict(d,steps=1)
If you are using a test data generator, it is good practice to define the steps, as mentioned in the documentation.
If you are predicting a single instance, no need to define the steps. Just make sure the argument (i.e. instance 'd') is not None, otherwise that error will show up. Some reshaping may also be necessary.
in my case i got the same error, i just reshaped the data to predict with numpy function reshape() to the shape of the data originally used to train the model.
I have single directory, dataset, which contains sub-folders(labels/classes) of images.
Here's the Sub-folders of animal images in dataset:
I want to split the dataset into train and test set for model.fit_generotar().
How can I do that?
Use glob to get file paths iterator.
You can then use scikit-learn's train-test split to get train and test data paths (use stratify parameter to get the same class distribution in test/train as in whole dataset).
The result would be two lists of paths, which you can write to appropriate test/train folders, and then you can apply generator's flow_from_directory method.
EDIT:
The second way would be to not use flow_from_directory, but load train/test sets (either load everything and use scikit-learn method or use what I've described before) and then use generator's flow method.
Also note that you might not want to use generators for test/validation data, since it would make comparing accuracy hard, since you won't have a fixed valid/test set.
I'm using Keras w/ Tensorflow backend to train a NN.
I'm using train_on_batch for training, which returns the loss on the given batch. How do I also get the output classification on that batch ? (I'd like to do some visualisations of the output)
To do that I currently do another call to predict to get the model output, but that's redundant since train_on_batch have already passed the input batch "forward".
In Caffe, when an image is fed forward, the intermediate layer outputs stay stored in net.blobs, but in Keras/Tensorflow it seems that if we want to get an intermediate output we have to rerun the computational graph for each intermediate output we want to access on CPU, as described here. Is there a way to access many/all intermediate layers' outputs without rerunning the graph for each ?
I don't mind having a tensorflow-specific workaround.
If you use the function API, this is pretty straight forward.
In addition to #MohamedEzz's answer, you can create a custom callback which can perform the operations you require during the training process. They have methods which will run your code onEpochEnd, onEpochStart, onTrainingEnd and so on...
This way you can preserve the batch.
I would like to speed up my LSTM network, but as I am using it for a OCR (where sequences have variable lenght), I can not use plain LSTM implementation. That is why I use "tf.nn.dynamic_rnn".
Based on benchmark of RNN in tensorflow (https://github.com/tensorflow/tensorflow/blob/754048a0453a04a761e112ae5d99c149eb9910dd/tensorflow/contrib/cudnn_rnn/python/kernel_tests/cudnn_rnn_ops_benchmark.py#L77), the CUDNN implementation is used for creating all model at once (it does not use "tf.nn.rnn" structure like others). I assume that it maybe impossible to use CUDNN with variable length, but maybe anybody success it?
Second this is using "tf.nn.bidirectional_dynamic_rnn", as I would like to use Bi-LSTM for OCR. But this should be resolved after implementing the first part.
Edit: It looks like "tf.contrib.cudnn_rnn.CudnnLSTM" have "bidirectional" implementation inside. So the only unknown this is that CUDNN can be used with variable input sequence.
Or maybe any working example which use 'CudnnLSTM' would be helpfull.
Just found this:
tf.contrib.cudnn_rnn.CudnnLSTM currently does not support batches with sequences of different length, thus this is normally not an option to use.
Source: http://returnn.readthedocs.io/en/latest/tf_lstm_benchmark.html
TensorFlow will soon finally have support for variable sequence lengths: https://github.com/tensorflow/tensorflow/blob/2f672ee9562a452f8dbfa259a8ccec56367e9b17/tensorflow/contrib/cudnn_rnn/python/layers/cudnn_rnn.py#L389
It looks like it landed too late for 1.13, so it'll probably only be available on TensorFlow 1.14.
You can try it out today by installing the tf-nightly-gpu package and passing sequence_lengths=lengths where lenghts is a tf.int32 Tensor with shape [batch_size], containing the lengths of each sequence in your batch.
I tried to follow the Cifar10 example. However, I want to replace the file reading with the Numpy array. There are a few benefits for doing that:
Simpler code (I want to remove the binary file parsing)
Simpler graph and visualization --> easier to explain to other audience
Small perf improvement (due to I/O and parsing)?
What would be a simple way to do it?
You need to get the tensor reshape_image by either:
giving it a name
finding its default name, with Tensorboard for instance
reshaped_image = tf.cast(read_input.uint8image, tf.float32, name="float_image")
Then you can feed your numpy array using a feed_dict like:
reshaped_image = tf.get_default_graph().get_tensor_by_name("float_image")
sess.run(loss, feed_dict={reshaped_image: your_numpy})
The same goes for labels.