I have this problem: I concatenate correctly some outputs from different conv layers. I train the model. Everything is fine up to the training. I save json model and weights.
When I load the model from another script using json API, I have this error:
ValueError: Concatenate layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 12, 12, 512), (None, None, None, 512)]
This happens only when I import the saved model.
More details: I have an output from a Conv2 (12, 12, 512) and from another one that matches. The proof is the fact that I can train without any problem (and actually I plot the summary and all the output_shape are correctly defined... no 'None' in shapes but the batch size).
I also tried to add in keras.json image_data_format. But I still have this issue.
I use keras '2.1.2' and tensorflow '1.2.0'. I use the functional API of keras.
Any suggestions?
Related
I am required to calculate the following in Paraview:
How can I calculate the transpose used in the above formula ? Basically I would like to know how to calculate the transpose of a matrix in Paraview.
As suggested by #Nico Vuaille, you should make use of Numpy support in ParaView. Simply apply a Programmable Filter to the dataset of interest, and supply a script comparable to the following.
import numpy as np
u = inputs[0].PointData['Velocity']
# Calculate gradient here, say uGrad
output.PointData.append(uGrad, 'Gradient')
EDIT: I have actually tried to generate your calculation with one of my datasets and realised that my answer and comments are not so helpful. Therefore, this is what I would suggest now, which should work:
Load your dataset in ParaView
Apply a Gradient / Gradient Of Unstructured Dataset filter on your dataset and select the velocity field as the input field (I used Gradient Of Unstructured Dataset, from which you have the possibility to also directly work out both divergence and vorticity fields).
Apply a Programmable Filter filter to the resulting dataset you obtained from the previous step and supply the code below.
Script
import numpy as np
grad = inputs[0].PointData['Gradients']
omega = (grad - np.transpose(grad, axes=(0, 2, 1))) / 2
output.PointData.append(omega, 'Omega')
You should end up with another item in your ParaView pipeline that only contains the expected Omega.
EDIT 2: The input file is using the XMDF format. When loaded into ParaView, it is interpreted as a Multi-Block Dataset of Blocks. As a result, the code snippet provided to the Script argument of Programmable Filter has to be updated to:
import paraview.vtk.numpy_interface.dataset_adapter as dsa
for i in range(inputs[0].GetNumberOfBlocks()):
data = dsa.WrapDataObject(inputs[0].GetBlock(i))
grad = data.PointData['Gradients']
omega = (grad - np.transpose(grad, axes=(0, 2, 1))) / 2
data.PointData.append(omega, 'Omega')
output.SetBlock(i, data.VTKObject)
I think this can be easily computed using Python calculator (no need for programmable filter):
To compute the gradient, type:
gradient(u)
To compute the symmetric part of the tensor gradient(u):
strain(u)
To compute the non-symmetric part, Omega, of the gradient tensor:
gradient(u) - strain(u)
Note that that the gradient(u) tensor can be written as follows:
I'm familiarizing myself with Pyspark and SparkML at the moment. To do so I use the titanic dataset to train a GLM for predicting the 'Fare' in that dataset.
I'm following closely the Spark documentation. I do get a working model (which I call glm_fare) but when I try to assess the trained model using summary I get the following error message:
RuntimeError: No training summary available for this GeneralizedLinearRegressionModel
Why is this?
The code for training was as such:
glm_fare = GeneralizedLinearRegression(
labelCol="Fare",
featuresCol="features",
predictionCol='prediction',
family='gamma',
link='log',
weightCol='wght',
maxIter=20
)
glm_fit = glm_fare.fit(training_df)
glm_fit.summary
Just in case someone comes across this question, I ran into this problem as well and it seems that this error occurs when the Hessian matrix is not invertible. This matrix is used in the maximization of the likelihood for estimating the coefficients.
The matrix is not invertible if one of the eigenvalues is 0, which occurs when there is multicollinearity in your variables. This means that one of the variables can be predicted with a linear combination of the other variables. Consequently, the effect of each of the variables cannot be identified with any significance.
A possible solution would be to find the variables that are (multi)collinear and remove one of them from the regression. Note however that multicollinearity is only a problem if you want to interpret the coefficients and not when the model is used for prediction.
It is documented possibly there could be no summary available for a model in GeneralizedLinearRegressionModel docs.
However you can do an initial check to avoid the error:
glm_fit.hasSummary() which is a public boolean method.
Using it as
if glm_fit.hasSummary():
print(glm_fit.summary)
Here is a direct like to the Pyspark source code
and the GeneralizedLinearRegressionTrainingSummary class source code and where the error is thrown
Make sure your input variables for one hot encoder starts from 0.
One error I made that caused summary not created is, I put quarter(1,2,3,4) directly to one hot encoder, and get a vector of length 4, and one column is 0. I converted quarter to 0,1,2,3 and problem solved.
My goal is to have an autoencoding network where I can train the identity function and then do forward passes yielding a reconstruction of the input.
For this, I'm trying to use VariationalAutoencoder, e.g. something like:
MultiLayerConfiguration conf = new NeuralNetConfiguration.Builder()
.seed(77147718)
.trainingWorkspaceMode(WorkspaceMode.NONE)
.gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue)
.gradientNormalizationThreshold(1.0)
.optimizationAlgo(OptimizationAlgorithm.CONJUGATE_GRADIENT)
.list()
.layer(0, new VariationalAutoencoder.Builder()
.activation(Activation.LEAKYRELU)
.nIn(100).nOut(15)
.encoderLayerSizes(120, 60, 30)
.decoderLayerSizes(30, 60, 120)
.pzxActivationFunction(Activation.IDENTITY)
.reconstructionDistribution(new BernoulliReconstructionDistribution(Activation.SIGMOID.getActivationFunction()))
.build())
.pretrain(true).backprop(false)
.build();
However, VariationalAutoencoder seems to be designed for training (and providing) mappings from an input to an encoded version, i.e. a vector of size 100 to a vector of size 15 in above example configuration.
However, I'm not particularly interested in the encoded version, but would like to train a mapping of a 100-vector to itself. Then, I'd like to run a other 100-vectors through it and get back their reconstructed versions.
But even when looking at the API of of the VariationalAutoencoder (or AutoEncoder too), I can't figure out how to do this. Or are those layers not designed for this kind of "end-to-end usage" and I would have to manually construct an autoencoding network?
You can see how to use the VAE layer to extract averaged reconstructions from the variational example.
There's two methods for getting the reconstruction from a variational layer. The standard is generateAtMeanGivenZ Which will draw samples from the layer and give you the average. If you want raw samples you can use generateRandomGivenZ. See the javadoc page for all the other methods.
I have two input datafiles to use in orange, one corresponds to the train set (with targets "A", "B" and "C") and the other to the unknown samples ( with targets "D" and "E" to be able to identify the unknown samples in the scatterplot of the two first principal components).
I have applied PCA to the train dataset and through a python script i have reapplied the PCA transformation to the test dataset, however the result have a ? in the target value for all entries in the unknown samples set.
I have tried to merge the train and unknown samples sets with the merge table widget, and apparently it does the same, all samples in train are correct, but the unknown samples have ? as targets.
The only way i managed to have this running properly is to have unknown samples and train set on the same input file. Which is not practical for obvious reasons.
Is there any way to fix this?
Please note that i have tried to change the domain.class_var and the target value directly on the transformed unknown samples, but it also alters the domain of the train dataset. Apparently when the new table is created it just have a reference to the domain of the original train data after PCA.
I have managed it by converting the data into numpy arrays concatenate them and then back to table.
Here is the code if anyone is interested:
import numpy
from Orange.data.table import Table
from Orange.data import Domain, DiscreteVariable, ContinuousVariable
trnsfrmd_knwn_data = numpy.array(in_object)
trnsfrmd_unkwn_data = numpy.array(Table(in_object.domain,in_data))
ndx = list(set(trnsfrmd_knwn_data[:,len(trnsfrmd_knwn_data[0])-1].tolist()))[-1] + 1
trnsfrmd_unkwn_data[:,len(trnsfrmd_knwn_data[0])-1] = numpy.array([i for i in range(0, len(trnsfrmd_unkwn_data))]) + ndx
targets = in_object.domain.class_var.values + in_data.domain.class_var.values
dm = Domain([ContinuousVariable(x.name) for x in in_object.domain.attributes], DiscreteVariable('region', values=targets))
out_data = Table.from_numpy(dm, numpy.append(trnsfrmd_knwn_data,trnsfrmd_unkwn_data,axis=0))
Im new to using Matlab and i'm trying to achieve the following situation:
I've one dataset of 7000+ entries. The goal is to train a classification tree (fitctree) on this data. I've seperated the data into a matrix with observations (predictors) and a matrix with classes(class). To partition the data i'm using cvpartition. Everything works fine up until this point.
Problem: I want to create three subsets with data: 1 training set, 1 validation set and 1 testing set. I want to train the tree using the training set, and validate its performance using the validation set. After tweeking the parameters I want to run the final test on the test data partition.
To partition the data I tried creating a cvpartition, which works, e.g.
cvpart = cvpartition(class, 'k', 10);
and then performing another cvpartition on that testing set, seperating this into another two sets:
cvpart2 = cvpartition(cvpart.TestSize, 'k', 10);
Sadly, when validating the performance of the tree this doesn't seem to work. When I skip the seond cvpartition, and validate the performance on the test set of cvpart, the model performs perfectly.
Update: after days I found that it seems to work when using it in this way:
cvpart2 = cvpartition(cvpart.TrainSize, 'k', 10);
Anyone care to explain me why it does work in this way, but not when using the test set?
Hope you guys can help me out;)
Kind regards.