Ggtcf

Cross compiling for RPi - error while loading shared libraries

Do I have a twin with permutated remainders?

Why are electrically insulating heatsinks so rare? Is it just cost?

Revoked SSL certificate

Today is the Center

Why doesn't Newton's third law mean a person bounces back to where they started when they hit the ground?

Perform and show arithmetic with LuaLaTeX

How do I deal with an unproductive colleague in a small company?

Why can't I see bouncing of a switch on an oscilloscope?

Replacing matching entries in one column of a file by another column from a different file

Paid for article while in US on F-1 visa?

Why doesn't H₄O²⁺ exist?

Unable to deploy metadata from Partner Developer scratch org because of extra fields

What defenses are there against being summoned by the Gate spell?

Can a vampire attack twice with their claws using Multiattack?

A case of the sniffles

If human space travel is limited by the G force vulnerability, is there a way to counter G forces?

Can you really stack all of this on an Opportunity Attack?

Why is Minecraft giving an OpenGL error?

What's the point of deactivating Num Lock on login screens?

Is it possible to run Internet Explorer on OS X El Capitan?

How old can references or sources in a thesis be?

NMaximize is not converging to a solution

Is it unprofessional to ask if a job posting on GlassDoor is real?

ValueError: cannot reshape array of size 9575706 into shape (9575706,137,1)

Char-RNN in TensorflowDynamic LSTM model in TensorflowString Input output representation in RNN Variational autoencoderValueError: cannot reshape array of size 30470400 into shape (50,1104,104)Keras LSTM Accuracy too highKeras error Error when checking target: expected activation_1 to have 2 dimensions, but got array with shape (10, 5, 95)Can anybody help me implement hybrid embedding model using keras library as shown in the attached figureVariable Length RNN Models with Long SequencesEmbedding version seq2seq model (Keras)Feeding the input sample by sample (no sequences) in a recurrent neural network

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty height:90px;width:728px;box-sizing:border-box;

0

I am trying to build a generative RNN-LSTM model, based off this repo: https://github.com/flawnson/Molecule_generating_RNN/blob/master/final_model.py

When trying to re-shape input X to be [samples, time steps, features], the input format for the recurrent model, it says i cannot re-shape it.

enter n_chars = len(raw_text) 
n_vocab = len(unique_chars)
print ("Total number of characters in the file is: ", n_chars)
# Preparing datasets by matching the dataset lengths (dataX will be the SMILES strings and dataY will be individual characters in the SMILE string)
seq_length = 137
dataX = []
dataY = []
for i in range (0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataX.append(char_to_int[seq_out])
n_patterns = len(dataX)
X = np.reshape (dataX, (n_patterns, seq_length, 1)

numpy machine-learning keras reshape recurrent-neural-network

share|improve this question

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  How far did you get? I tried it out, it's running with a fresh installation of keras, tensorflow and numpy, but now it's training the model for maybe 10 hours or some days consuming 25gb of ram...
  
  – mimimi
  Mar 9 at 3:52
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  It finished after 10h without error.
  
  – mimimi
  Mar 9 at 14:03
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I managed to fix it on a new installation, but I was getting a lot of RAM consumption.
  
  – Seyone Chithrananda
  Mar 9 at 15:10
  

  
  
  
  

add a comment | 

0

I am trying to build a generative RNN-LSTM model, based off this repo: https://github.com/flawnson/Molecule_generating_RNN/blob/master/final_model.py

When trying to re-shape input X to be [samples, time steps, features], the input format for the recurrent model, it says i cannot re-shape it.

enter n_chars = len(raw_text) 
n_vocab = len(unique_chars)
print ("Total number of characters in the file is: ", n_chars)
# Preparing datasets by matching the dataset lengths (dataX will be the SMILES strings and dataY will be individual characters in the SMILE string)
seq_length = 137
dataX = []
dataY = []
for i in range (0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataX.append(char_to_int[seq_out])
n_patterns = len(dataX)
X = np.reshape (dataX, (n_patterns, seq_length, 1)

numpy machine-learning keras reshape recurrent-neural-network

share|improve this question

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  How far did you get? I tried it out, it's running with a fresh installation of keras, tensorflow and numpy, but now it's training the model for maybe 10 hours or some days consuming 25gb of ram...
  
  – mimimi
  Mar 9 at 3:52
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  It finished after 10h without error.
  
  – mimimi
  Mar 9 at 14:03
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I managed to fix it on a new installation, but I was getting a lot of RAM consumption.
  
  – Seyone Chithrananda
  Mar 9 at 15:10
  

  
  
  
  

add a comment | 

I am trying to build a generative RNN-LSTM model, based off this repo: https://github.com/flawnson/Molecule_generating_RNN/blob/master/final_model.py

When trying to re-shape input X to be [samples, time steps, features], the input format for the recurrent model, it says i cannot re-shape it.

enter n_chars = len(raw_text) 
n_vocab = len(unique_chars)
print ("Total number of characters in the file is: ", n_chars)
# Preparing datasets by matching the dataset lengths (dataX will be the SMILES strings and dataY will be individual characters in the SMILE string)
seq_length = 137
dataX = []
dataY = []
for i in range (0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataX.append(char_to_int[seq_out])
n_patterns = len(dataX)
X = np.reshape (dataX, (n_patterns, seq_length, 1)

numpy machine-learning keras reshape recurrent-neural-network

share|improve this question

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

enter n_chars = len(raw_text) 
n_vocab = len(unique_chars)
print ("Total number of characters in the file is: ", n_chars)
# Preparing datasets by matching the dataset lengths (dataX will be the SMILES strings and dataY will be individual characters in the SMILE string)
seq_length = 137
dataX = []
dataY = []
for i in range (0, n_chars - seq_length, 1):
seq_in = raw_text[i:i + seq_length]
seq_out = raw_text[i + seq_length]
dataX.append([char_to_int[char] for char in seq_in])
dataX.append(char_to_int[seq_out])
n_patterns = len(dataX)
X = np.reshape (dataX, (n_patterns, seq_length, 1)

share|improve this question

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

share|improve this question

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81

asked Mar 9 at 0:56

Seyone ChithranandaSeyone Chithrananda

81