In this example, the guide step is defined as follows
def guide(params):
# returns the Bernoulli probablility
alpha = pyro.param(
"alpha", torch.tensor(params[0]), constraint=constraints.positive
)
beta = pyro.param(
"beta", torch.tensor(params[1]), constraint=constraints.positive
)
return pyro.sample("beta_dist", dist.Beta(alpha, beta))
svi = pyro.infer.SVI(
model=conditioned_data_model,
guide=guide,
optim=pyro.optim.SGD({"lr": 0.001, "momentum": 0.8}),
loss=pyro.infer.Trace_ELBO(),
)
params_prior = [prior.concentration1, prior.concentration0]
# Iterate over all the data and store results
losses, alpha, beta = [], [], []
pyro.clear_param_store()
num_steps = 3000
for t in range(num_steps):
losses.append(svi.step(params_prior))
alpha.append(pyro.param("alpha").item())
beta.append(pyro.param("beta").item())
posterior_vi = dist.Beta(alpha[-1], beta[-1])
However, running the above step gives the following error, what does those hints of fix mean and how to fix it accordingly?
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
Input In [9], in <cell line: 15>()
14 num_steps = 3000
15 for t in range(num_steps):
---> 16 losses.append(svi.step(params_prior))
17 alpha.append(pyro.param("alpha").item())
18 beta.append(pyro.param("beta").item())
ValueError: at site "data_dist", invalid log_prob shape
Expected [], actual [100, 1]
Try one of the following fixes:
- enclose the batched tensor in a with pyro.plate(...): context
- .to_event(...) the distribution being sampled
- .permute() data dimensions
Related
I am trying to do feature selection using feature forward method.
Tried previously answered questions but didn't get any proper solution. My code is as follows:
def forward_selection_rf(data, target, number_of_features=14):
# adapt number of features to select: if requested number
# is greater than features availabe, go for 75% of the
# features instead
if number_of_features > len(data.columns):
print("SFS: Wanted " + str(number_of_features) + " from " + str(len(data.columns)) + " featurs. Sanifying to 75%")
number_of_features = 0.75
# Sequential Forward Selection(sfs)
sfs1 = sfs(RandomForestClassifier(
n_estimators=70,
criterion='gini',
max_depth=15,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
bootstrap=True,
oob_score=False,
n_jobs=-1,
random_state=0,
verbose=0,
warm_start=False,
class_weight='balanced'
),
n_features_to_select=14,
direction='forward',
scoring = 'roc_auc',
cv = 5,
n_jobs = 3)
sfs1.fit(data, target)
return sfs1
compiler gives runtime error as follows:
forward_selection_rf(X, y, number_of_features=14)
Traceback (most recent call last):
File "C:\Users\drash\AppData\Local\Temp\ipykernel_37980\1091017691.py", line 1, in <module>
forward_selection_rf(X, y, number_of_features=14)
File "C:\Users\drash\OneDrive\Desktop\Howto Health\untitled3.py", line 102, in forward_selection_rf
TypeError: __init__() got an unexpected keyword argument 'n_features_to_select'
For a long time I was able to add data and fit, then plot the curve with data. But recently I get this:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-6-6f645a2744bc> in <module>
1 poland = prepare_data(europe_data, 'Poland')
----> 2 plot_all(poland, max_y=400000)
3 poland
~/Pulpit/library.py in plot_all(country, max_x, max_y)
43 def plot_all(country, max_x = 1000, max_y = 500000):
44
---> 45 parameters_logistic = scipy.optimize.curve_fit(func_logistic, country['n'], country['all'])[0]
46 parameters_expo = scipy.optimize.curve_fit(func_expo, country['n'], country['all'])[0]
47
/usr/local/lib64/python3.6/site-packages/scipy/optimize/minpack.py in curve_fit(f, xdata, ydata, p0, sigma, absolute_sigma, check_finite, bounds, method, jac, **kwargs)
787 cost = np.sum(infodict['fvec'] ** 2)
788 if ier not in [1, 2, 3, 4]:
--> 789 raise RuntimeError("Optimal parameters not found: " + errmsg)
790 else:
791 # Rename maxfev (leastsq) to max_nfev (least_squares), if specified.
RuntimeError: Optimal parameters not found: Number of calls to function has reached maxfev = 800.
Here are all Python Jupyter Notebook files: https://files.fm/u/zj7cc6ne#sign_up
How to solve this?
scipy.optimize.curve_fit takes a keyword argument p0.
Initial guess for the parameters (length N). If None, then the initial
values will all be 1 (if the number of parameters for the function can
be determined using introspection, otherwise a ValueError is raised).
If the defaults 1 are too far of from the result the algorithm may not converge. Try to put some values that make sense for your problem.
I am having a weird "ValueError: mean must be 1 dimensional" when I am trying to build a Hierarchical GL-LVM model. Basically I'm trying to reproduce this paper: Hierarchical Gaussian Process Latent Variable Models using GPflow.
Therefore I implemented my own new model as follow:
class myGPLVM(gpflow.models.BayesianModel):
def __init__(self, data, latent_data, x_data_mean, kernel):
super().__init__()
print("GPLVM")
self.kernel0 = kernel[0]
self.kernel1 = kernel[1]
self.mean_function = Zero()
self.likelihood0 = gpflow.likelihoods.Gaussian(1.0)
self.likelihood1 = gpflow.likelihoods.Gaussian(1.0)
# make some parameters
self.data = (gpflow.Parameter(x_data_mean), gpflow.Parameter(latent_data), data)
def hierarchy_ll(self):
x, h, y = self.data
K = self.kernel0(x)
num_data = x.shape[0]
k_diag = tf.linalg.diag_part(K)
s_diag = tf.fill([num_data], self.likelihood0.variance)
ks = tf.linalg.set_diag(K, k_diag + s_diag)
L = tf.linalg.cholesky(ks)
m = self.mean_function(x)
return multivariate_normal(h, m, L)
def log_likelihood(self):
"""
Computes the log likelihood.
.. math::
\log p(Y | \theta).
"""
x, h, y = self.data
K = self.kernel1(h)
num_data = h.shape[0]
k_diag = tf.linalg.diag_part(K)
s_diag = tf.fill([num_data], self.likelihood1.variance)
ks = tf.linalg.set_diag(K, k_diag + s_diag)
L = tf.linalg.cholesky(ks)
m = self.mean_function(h)
# [R,] log-likelihoods for each independent dimension of Y
log_prob = multivariate_normal(y, m, L). # <- trows the error!
log_prob_h = self.hierarchy_ll()
log_likelihood = tf.reduce_sum(log_prob) + tf.reduce_sum(log_prob_h)
return log_likelihood
The model seems to work with a toy example:
from sklearn.datasets.samples_generator import make_blobs
X, y = make_blobs(n_samples=40, centers=3, n_features=12, random_state=2)
Y = tf.convert_to_tensor(X, dtype=default_float())
but fails and trough me the error when I am trying with a bvh file (the one from the paper actually). I also used Lawrence's code to read my bvh from mocap which I modified to fit python3
Anyway, it's been few a days and I am out of ideas. I tried multiple way to force my mean array "m" to be of one dimensional but nothing worked. I also tried with the "three_phase_oil_flow" dataset from the first GPLVM paper which works as well.
Therefore, I would assume that my model is correct, or at least I got some optimisation going on, and would think that perhaps the bvh reader could be the cause. But the data seems all fine to me... Especially I don't understand why when forcing multivariate function like:
m = np.zeros((np.shape(m)[0], 1))
log_prob = multivariate_normal(y, m, L)
or even with the gpflow Zero function
m = Zero(h)
log_prob = multivariate_normal(y, m, L)
it still trows me the error. Any help will be highly appreciated.
edited thanks to: Artem Artemev
The rest of the code if anyone wants to try to reproduce:
https://github.com/michaelStettler/h-GPLVM
error flow:
(venv) MacBookMichael2:stackOverflow michaelstettler$ python3 HGPLVM.py
(199, 96)
shape Y (199, 3, 38)
2020-01-26 17:00:48.104029: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-01-26 17:00:48.113609: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7f8dd5ff5410 executing computations on platform Host. Devices:
2020-01-26 17:00:48.113627: I tensorflow/compiler/xla/service/service.cc:175] StreamExecutor device (0): Host, Default Version
shape Y (199, 38)
Number of points: 199 and Number of dimensions: 38
shape x_mean_latent (199, 8)
shape x_mean_init (199, 2)
HGPLVM
gpr_data (199, 2) (199, 8) (199, 38)
2020-01-26 17:00:48.139003: W tensorflow/python/util/util.cc:299] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them.
shape m (199, 1)
Traceback (most recent call last):
File "HGPLVM.py", line 131, in <module>
_ = opt.minimize(closure, method="bfgs", variables=model.trainable_variables, options=dict(maxiter=maxiter))
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 60, in minimize
**scipy_kwargs)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/_minimize.py", line 594, in minimize
return _minimize_bfgs(fun, x0, args, jac, callback, **options)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 998, in _minimize_bfgs
gfk = myfprime(x0)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 327, in function_wrapper
return function(*(wrapper_args + args))
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 73, in derivative
self(x, *args)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 65, in __call__
fg = self.fun(x, *args)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 72, in _eval
loss, grads = _compute_loss_and_gradients(closure, variables)
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/optimizers/scipy.py", line 116, in _compute_loss_and_gradients
loss = loss_cb()
File "HGPLVM.py", line 127, in closure
return - model.log_marginal_likelihood()
File "/Users/michaelstettler/PycharmProjects/GPflow/venv/lib/python3.6/site-packages/gpflow/models/model.py", line 45, in log_marginal_likelihood
return self.log_likelihood(*args, **kwargs) + self.log_prior()
File "HGPLVM.py", line 62, in log_likelihood
log_prob = multivariate_normal(y, m, L)
File "mtrand.pyx", line 3729, in numpy.random.mtrand.RandomState.multivariate_normal
ValueError: mean must be 1 dimensional
I would recommend posting a working MWE code. I have tried to use your code snippets, but it gives me errors.
I don't have issues with multivariate_normal function. If you have localised the issue correctly you can debug TF2.0 more thoroughly and find the place that causes that exception. Here is the code which I'm running:
In [2]: from sklearn.datasets.samples_generator import make_blobs
...: X, y = make_blobs(n_samples=40, centers=3, n_features=12, random_state=2)
In [10]: m = np.zeros((np.shape(y)[0], 1))
In [11]: m.shape
Out[11]: (40, 1)
In [12]: y.shape
Out[12]: (40,)
In [13]: L = np.eye(m.shape[0])
In [15]: gpflow.logdensities.multivariate_normal(y, m, L)
Out[15]:
<tf.Tensor: shape=(40,), dtype=float64, numpy=
array([ -56.75754133, ...])>
Hello consider following code
# load the mnist training data CSV file into a list
training_data_file = open("Training_Set/mnist_train_100.csv", 'r')
training_data_list = training_data_file.readlines()
training_data_file.close()
for record in training_data_list:
all_values = record.split(',')
x_inputs = (np.asfarray(all_values[1:]) / 255.0 * 0.99) + 0.01
print("xinput=" + str(x_inputs))
print(len(training_data_list))
MyCompleteInput = np.array(x_inputs,len(training_data_list))
I want to put x_inputs and len(training_data_list) into an array so if I print the shape of the array I get an output of (784,100).
But if I run my code I get following error:
TypeError Traceback (most recent call last)
<ipython-input-38-b0f129f57bcb> in <module>()
11 print("xinput=" + str(x_inputs))
12 print(len(training_data_list))
---> 13 MyCompleteInput = np.array(x_inputs,len(training_data_list))
14
15
TypeError: data type not understood
Can somebody help me out? tnx
The line will be
MyCompleteInput = np.array((x_inputs,len(training_data_list)))
Do this and your error will be gone. You need to add another set of parantheses for specifying the size.
Using the MNIST tutorial of Tensorflow, I try to make a convolutional network for face recognition with the "Database of Faces".
The images size are 112x92, I use 3 more convolutional layer to reduce it to 6 x 5 as adviced here
I'm very new at convolutional network and most of my layer declaration is made by analogy to the Tensorflow MNIST tutorial, it may be a bit clumsy, so feel free to advice me on this.
x_image = tf.reshape(x, [-1, 112, 92, 1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)
W_conv3 = weight_variable([5, 5, 64, 128])
b_conv3 = bias_variable([128])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)
W_conv4 = weight_variable([5, 5, 128, 256])
b_conv4 = bias_variable([256])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4 = max_pool_2x2(h_conv4)
W_conv5 = weight_variable([5, 5, 256, 512])
b_conv5 = bias_variable([512])
h_conv5 = tf.nn.relu(conv2d(h_pool4, W_conv5) + b_conv5)
h_pool5 = max_pool_2x2(h_conv5)
W_fc1 = weight_variable([6 * 5 * 512, 1024])
b_fc1 = bias_variable([1024])
h_pool5_flat = tf.reshape(h_pool5, [-1, 6 * 5 * 512])
h_fc1 = tf.nn.relu(tf.matmul(h_pool5_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder("float")
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
print orlfaces.train.num_classes # 40
W_fc2 = weight_variable([1024, orlfaces.train.num_classes])
b_fc2 = bias_variable([orlfaces.train.num_classes])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)
My problem appear when the session run the "correct_prediction" op which is
tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
At least I think given the error message:
W tensorflow/core/common_runtime/executor.cc:1027] 0x19369d0 Compute status: Invalid argument: Incompatible shapes: [8] vs. [20]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](ArgMax, ArgMax_1)]]
Traceback (most recent call last):
File "./convolutional.py", line 133, in <module>
train_accuracy = accuracy.eval(feed_dict = {x: batch[0], y_: batch[1], keep_prob: 1.0})
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 405, in eval
return _eval_using_default_session(self, feed_dict, self.graph, session)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2728, in _eval_using_default_session
return session.run(tensors, feed_dict)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 345, in run
results = self._do_run(target_list, unique_fetch_targets, feed_dict_string)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 419, in _do_run
e.code)
tensorflow.python.framework.errors.InvalidArgumentError: Incompatible shapes: [8] vs. [20]
[[Node: Equal = Equal[T=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"](ArgMax, ArgMax_1)]]
Caused by op u'Equal', defined at:
File "./convolutional.py", line 125, in <module>
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 328, in equal
return _op_def_lib.apply_op("Equal", x=x, y=y, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 633, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1710, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 988, in __init__
self._traceback = _extract_stack()
It looks like the y_conv output a matrix of shape 8 x batch_size instead of number_of_class x batch_size
If I change the batch size from 20 to 10, the error message stay the same but instead [8] vs. [20] I get [4] vs. [10]. So from that I conclude that the problem may come from the y_conv declaration (last line of the code above).
The loss function, optimizer, training, etc declarations is the same as in the MNIST tutorial:
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
sess.run((tf.initialize_all_variables()))
for i in xrange(1000):
batch = orlfaces.train.next_batch(20)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict = {x: batch[0], y_: batch[1], keep_prob: 1.0})
print "Step %d, training accuracy %g" % (i, train_accuracy)
train_step.run(feed_dict = {x: batch[0], y_: batch[1], keep_prob: 0.5})
print "Test accuracy %g" % accuracy.eval(feed_dict = {x: orlfaces.test.images, y_: orlfaces.test.labels, keep_prob: 1.0})
Thanks for reading, have a good day
Well, after a lot debugging, I found that my issue was due to a bad instantiation of the labels. Instead of creating arrays full of zeros and replace one value by one, I created them with random value! Stupid mistake. In case someone wondering what I did wrong there and how I fix it here is the change I made.
Anyway during all the debugging I made, to find this mistake, I found some useful information to debug this kind of problem:
For the cross entropy declaration, the tensorflow's MNIST tutorial use a formula that can lead to NaN value
This formula is
cross_entropy = -tf.reduce_sum(y_ * tf.log(y_conv))
Instead of this, I found two ways to declare it in a safer fashion:
cross_entropy = -tf.reduce_sum(y_ * tf.log(tf.clip_by_value(y_conv, 1e-10, 1.0)))
or also:
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logit, y_))
As mrry says. printing the shape of the tensors can help to detect shape anomaly.
To get the shape of a tensor just call his get_shape() method like this:
print "W shape:", W.get_shape()
user1111929 in this question use a debug print that help me assert where the problem come from.