LSTMCell | Implement modern LSTM cell tensorflow and test | Machine Learning library

I'm trying to implement a custom activation function (pentanh) based on the Tanh activation. However, when I add this fuction to my model, it raises a ValueError.

The custom activation fuction:

I'm trying to do a prediction on new text examples, where I want the prediction to return a probability output for each example.

This is my learning model:

I am trying to implement an autoregressive seq-2-seq RNN to predict time series data, as shown in this TensorFlow tutorial. The model consists of a custom model class, inheriting from tf.keras.Model, of which the code can be found below. I have used this model for time series prediction with as input data a (15, 108) dataset (dimensions: (sequence length, input units)) and as output data a (10, 108) dataset.

Although training was succesful, I have not succeeded to successfully save and reload the model to evaluate previously trained models on a test set. I have tried looking for solutions on the internet, but none of them seem to work so far. Possibly this is due to since it is a custom model trained using eager execution, as multiple threads could not resolve saving the model in these conditions.

Could anybody give me tips on how to resolve this problem. Any help is greatly appreciated, thanks!

Thusfar, I have loaded the model using tf.keras.models.load_model(filepath) and tried the following options for saving. The code of both options can be found below:

• Saving using the keras.callbacks.ModelCheckpoint function. However, only a .ckpt.data-00000-of-00001 and a .ckpt.index file was returned (so no .meta or .pb file), which I was unable to open
• Saving using the tf.saved_model.save function and loading the model with which resulted in the following error:

Autoencoder underfits timeseries reconstruction and just predicts average value.

Here is a summary of my attempt at a sequence-to-sequence autoencoder. This image was taken from this paper: https://arxiv.org/pdf/1607.00148.pdf

Encoder: Standard LSTM layer. Input sequence is encoded in the final hidden state.

Decoder: LSTM Cell (I think!). Reconstruct the sequence one element at a time, starting with the last element x[N].

Decoder algorithm is as follows for a sequence of length N:

1. Get Decoder initial hidden state hs[N]: Just use encoder final hidden state.
2. Reconstruct last element in the sequence: x[N]= w.dot(hs[N]) + b.
3. Same pattern for other elements: x[i]= w.dot(hs[i]) + b
4. use x[i] and hs[i] as inputs to LSTMCell to get x[i-1] and hs[i-1]

Here is my implementation, starting with the encoder:

I am trying to use A3C with LSTM for an environment where states has 12 inputs ranging from -5000 to 5000. I am using an LSTM layer of size 12 and then 2 fully connected hidden layers of size 256, then 1 fc for 3 action dim and 1 fc for 1 value function. The reward is in range (-1,1).

However during initial training I am unable to get good results.

My question is- Is this Neural Network good enough for this kind of environment.

Below is the code for Actor Critic

Below is my code, to create a caption for a video sequence

'''import tensorflow as tf import tensorflow.keras as keras import numpy as np print(tf.version)

class WordEmbeding(tf.keras.layers.Layer): def init(self,n_words,dim_hidden): super(WordEmbeding, self).init()

My network is a 1d CNN, I want to compute the number of FLOPs and params. I used public method 'flops_counter', but I am not sure the size of the input. When I run it with size(128,1,50), I get error 'Expected 3-dimensional input for 3-dimensional weight [128, 1, 50], but got 4-dimensional input of size [1, 128, 1, 50] instead'. When I run it with size(128,50), I get error 'RuntimeError: Given groups=1, weight of size [128, 1, 50], expected input[1, 128, 50] to have 1 channels, but got 128 channels instead'.

I am learning about tensorflow, and seq2seq problems for machine translation. For this I gave me the following task:

I created an Excel, containing random dates in different types, for example:

1. 05.09.2192
2. martes, 07 de mayo de 2329
3. Friday, 30 December, 2129

In my dataset, each type is occuring 1000 times. These are my train (X) value. My target (Y) values are in one half always in this type:

• 05.09.2192
• 07.03.2329
• 30.12.2129

And in another half in this type:

• Samstag, 12. Juni 2669
• Donnerstag, 1. April 2990
• Freitag, 10. November 2124

To make the model beeing able to differentiate these two Y values, another context information (C) is given as text:

1. Ausgeschrieben (written out)
2. Datum (date)

So some rows look like this:

So my goal is, to create a model, which is able to "translate" any date type to the german date type e.g. 05.09.2192.

The dataset contains 34.000 pairs.

To solve this, I use a character based tokenizer to transform text into integers:

I am trying to train a Actor Critic Model with LSTM in both actor and critic. I am new to all this and can not understand why "RuntimeError: Dimension out of range (expected to be in range of [-1, 0], but got 1)" is comming.

I am forwardPropagating from actor and getting error

below is my code and error message.I am using pytorch version 0.4.1

Can someone please help to check what is wrong with this code.