Develop Reference

tensorflow nonmaxsuppresion usage

I am trying to use nonmax suppresion on my output of CNN.
I am using
box = tf.image.non_max_suppression(
prediction[0],
[],
15,
iou_threshold=0.5,
name=None
)
where prediction[0] is 2d array , output of model.predict
However printing it outputs
Tensor("non_max_suppression/NonMaxSuppressionV2:0", shape=(?,), dtype=int32)
How to retrieve the coordinations of boxes from the output of non_max_suppresion?

This question is asked often in various forms, you should read the writeup here, it all applies to you just the same as it does to that question:
Working of TensorFlow feature columns
You should be creating a placeholder for the values your passing into tf.image.non_max_suppression
Then you should be calling
result_numpy = sess.run(box, feed_dict={placeholder:data})
What you printed was the symbolic representation of the math operation you defined, you haven't actually passed anything into tensorflow and asked it to perform the computation yet.

h2o python balance classes

I'm having problems implementing a simple balancing for an H2ORandomForestEstimator, I'm trying to reproduce a simple example found in Darren Cook's book written in R ('Practical Machine Learning with H2O - pag. 107).
Working on the Iris Dataset, firstly I artificially unbalance the target variable cutting out a good share of virginica keeping first 120 rows.
Then I build 3 models, a vanilla one, one where I set balance_classes as True, and a last one where I set balance_classes as True and I input a list for class_sampling_factors to oversample the virginica one. List is [1.0,1.0,2.5], referred to columns sorted alphabetically.
I train them, and then output confusion matrix for train for each one.
I'm expecting an unbalanced output for the first one, and a balanced one for the last two, while I have always the same result. I checked the documentation example in Python, and I can't see anything wrong (I may be tired as well).
This is my code:
data_unb = data[1:120,:] # messing up with target variable
train, valid = data_unb.split_frame([0.8], seed=12345)
m1 = h2o.estimators.random_forest.H2ORandomForestEstimator(seed=12345)
m2 = h2o.estimators.random_forest.H2ORandomForestEstimator(balance_classes=True, seed=12345)
m3 = h2o.estimators.random_forest.H2ORandomForestEstimator(balance_classes=True, class_sampling_factors=[1.0,1.0,2.5], seed=12345)
m1.train(x=list(range(4)),y=4,training_frame=train,validation_frame=valid,model_id='RF_defaults')
m2.train(x=list(range(4)),y=4,training_frame=train,validation_frame=valid,model_id='RF_balanced')
m3.train(x=list(range(4)),y=4,training_frame=train,validation_frame=valid,model_id='RF_class_sampling',)
m1.confusion_matrix(train)
m2.confusion_matrix(train)
m3.confusion_matrix(train)
This is my output:
my confusion matrices (wrong)
this is my expected output.
expected confusion matrices
What am I evidently missing? Thanks in advance.

You're not missing anything. The offset_column is available in H2O Random Forest, but it's not actually functional. The bug is documented here and should be fixed in the next stable release of H2O. Sorry about the confusion!
It should work for the rest of the H2O algos (except XGBoost). If you wanted to try on a GBM, for example, you'd see it working.

How to apply the torch.inverse() function of PyTorch to every sample in the batch?

This may seem like a basic question, but I am unable to work it through.
In the forward pass of my neural network, I have an output tensor of shape 8x3x3, where 8 is my batch size. We can assume each 3x3 tensor to be a non-singular matrix. I need to find the inverse of these matrices.
The PyTorch inverse() function only works on square matrices. Since I now have 8x3x3, how do I apply this function to every matrix in the batch in a differentiable manner?
If I iterate through the samples and append the inverses to a python list, which I then convert to a PyTorch tensor, should it be a problem during backprop? (I am asking since converting PyTorch tensors to numpy to perform some operations and then back to a tensor won't compute gradients during backprop for such operations)
I also get the following error when I try to do something like that.
a = torch.arange(0,8).view(-1,2,2)
b = [m.inverse() for m in a]
c = torch.FloatTensor(b)
TypeError: 'torch.FloatTensor' object does not support indexing

EDIT:
As of Pytorch version 1.0, torch.inverse now supports batches of tensors. See here. So you can simply use the built-in function torch.inverse
OLD ANSWER
There are plans to implement batched inverse soon. For discussion, see for example issue 7500 or issue 9102. However, as of the time of writing, the current stable version (0.4.1), no batch inverse operation is available.
Having said that, recently batch support for torch.gesv was added. This can be (ab)used to define your own batched inverse operation along the following lines:
def b_inv(b_mat):
eye = b_mat.new_ones(b_mat.size(-1)).diag().expand_as(b_mat)
b_inv, _ = torch.gesv(eye, b_mat)
return b_inv
I found that this gives good speed-ups over a for loop when running on GPU.

You could split the tensor using torch.functional.unbind(), apply inverse to every element of the result, and then stack back:
a = torch.arange(0,8).view(-1,2,2)
b = [t.inverse() for t in torch.functional.unbind(a)]
c = torch.functional.stack(b)

CNTK & python: How to pass input data to the eval func?

With CNTK I have created a network with 2 input neurons and 1 output neuron.
A line in the training file looks like
|features 1.567518 2.609619 |labels 1.000000
Then the network was trained with brain script. Now I want to use the network for predicting values. For example: Input data is [1.82, 3.57]. What ist the output from the net?
I have tried Python with the following code, but here I am new. Code does not work. So my question is: How to pass the input data [1.82, 3.57] to the eval function?
On stackoverflow there are some hints, here and here, but this is too abstract for me.
Thank you.
import cntk as ct
import numpy as np
z = ct.load_model("LR_reg.dnn", ct.device.cpu())
input_data= np.array([1.82, 3.57], dtype=np.float32)
pred = z.eval({ z.arguments[0] : input_data })
print(pred)

Here's the most defensive way of doing it. CNTK can be forgiving if you omit some of this when the network is specified with V2 constructs. Not sure about a network that was created with V1 code.
Basically you need a pair of braces for each axis. Which axes exist in Brainscript? There's a batch axis, a sequence axis and then the static axes of your network. You have one dimensional data so that means the following should work:
input_data= np.array([[[1.82, 3.57]]], dtype=np.float32)
This specifies a batch of one sequence, of length one, containing one 1d vector of two elements. You can also try omitting the outermost braces and see if you are getting the same result.
Update based on more information from the comment below, we should not forget that the V1 code also saved the part of the network that computes things like loss and accuracy. If we provide only the features, CNTK will complain that the labels have not been provided. There are two ways to deal with this issue. One possibility is to provide some fake labels, so that the network can evaluate these auxiliary operations. Another possibility is to identify the prediction and use that. If the prediction was called 'p' in V1, this python code
p = z.find_by_name('p')
should create a CNTK function that only needs the features in order to compute the prediction.

Pymc3: Optimizing parameters with multiple data?

I've designed a model using Pymc3, and I have some trouble optimizing it with multiple data.
The model is a bit similar to the coal-mining disaster (as in the Pymc3 tutorial for those who know it), except there are multiple switchpoints.
The output of the network is a serie of real numbers for instance:
[151,152,150,20,19,18,0,0,0]
with Model() as accrochage_model:
time=np.linspace(0,n_cycles*data_length,n_cycles*data_length)
poisson = [Normal('poisson_0',5,1), Normal('poisson_1',10,1)]
variance=3
t = [Normal('t_0',0.5,0.01), Normal('t_1',0.7,0.01)]
taux = [Bernoulli('taux_{}'.format(i),t[i]) for i in range(n_peaks)]
switchpoint = [Poisson('switchpoint_{}'.format(i),poisson[i])*taux[i] for i in range(n_peaks)]
peak=[Normal('peak_0',150,2),Normal('peak_1',50,2),Normal('peak_2',0,2)]
z_init=switch(switchpoint[0]>=time%n_cycles,0,peak[0])
z_list=[switch(sum(switchpoint[j] for j in range(i))>=time%n_cycles,0,peak[i]-peak[i-1]) for i in range(1,n_peaks)]
z=(sum(z_list[i] for i in range(len(z_list))))
z+=z_init
m =Normal('m', z, variance,observed=data)
I have multiple realisations of the true distribution and I'd like taking all of them into account while performing optimization of the parameters of the system.
Right now my "data" that appears in observed=data is just one list of results , such as:
[151,152,150,20,19,18,0,0,0]
What I would like to do is give not just one but several lists of results,
for instance:
data=([151,152,150,20,19,18,0,0,0],[145,152,150,21,17,19,1,0,0],[151,149,153,17,19,18,0,0,1])
I tried using the shape parameter and making data an array of results but none of it seemed to work.
Does anyone have an idea of how it's possible to do the inference so that the network is optimized for an entire dataset and not a single output?