I am trying to understand how I can define my own function in python, and then define its derivative so that it can be used in a GradientTape scope. I have found this answer which is for TensorFlow 1, and after modifying its code so that it runs in TensorFlow 2 I have the following code.
import tensorflow as tf
from tensorflow.python.framework import ops
import numpy as np
def np_mod(x,y):
return (x % y).numpy().astype(np.float32)
def modgrad(op, grad):
x = op.inputs[0] # the first argument (normally you need those to calculate the gradient, like the gradient of x^2 is 2x. )
y = op.inputs[1] # the second argument
return grad * 1, grad * tf.neg(tf.floordiv(x, y)) #the propagated gradient with respect to the first and second argument respectively
def py_function(func, inp, Tout, name=None, grad=None):
# Need to generate a unique name to avoid duplicates:
rnd_name = 'PyFuncGrad' + str(np.random.randint(0, 1E+8))
tf.RegisterGradient(rnd_name)(grad) # see _MySquareGrad for grad example
g = tf.compat.v1.get_default_graph()
with g.gradient_override_map({"PyFunc": rnd_name}):
return tf.py_function(func, inp, Tout, name=name)
def tf_mod(x,y, name=None):
with ops.op_scope([x,y], name, "mod") as name:
z = py_function(np_mod,
[x,y],
[tf.float32],
name=name,
grad=modgrad) # <-- here's the call to the gradient
return z[0]
with tf.compat.v1.Session() as sess:
x = tf.constant([0.3,0.7,1.2,1.7])
y = tf.constant([0.2,0.5,1.0,2.9])
z = tf_mod(x,y)
gr = tf.gradients(z, [x,y])
tf.compat.v1.initialize_all_variables().run()
print(x.eval(), y.eval(),z.eval(), gr[0].eval(), gr[1].eval())
And this code yields the following output from the print statement:
[0.3 0.7 1.2 1.7] [0.2 0.5 1. 2.9] [0.10000001 0.19999999 0.20000005 1.7 ] 0.0 0.0
It seems as if the gradients are just being set to 0, in the origional answer linked above the output which is obtained is the following:
[ 0.30000001 0.69999999 1.20000005 1.70000005] [ 0.2 0.5 1. 2.9000001] [ 0.10000001 0.19999999 0.20000005 1.70000005] [ 1. 1. 1. 1.] [ -1. -1. -1. 0.]
How could I modify this code so that it works correctly or, even better, how could I write this code in a way which works well with TF 2, not requiring tf.compat.v1.xyz?
Related
The graph compiles but NaN output values in objective function (although, random generated data as input).
# reference https://www.tensorflow.org/probability/api_docs/python/tfp/math/ode/Solver
# reference https://www.tensorflow.org/probability/api_docs/python/tfp/optimizer/differential_evolution_minimize
import tensorflow as tf
import tensorflow_probability as tfp
from tensorflow_probability import distributions as tfd
tf.executing_eagerly()
population_size = 40
initial_population = (tf.random.normal([population_size]),
tf.random.normal([population_size]))
pi = tf.constant(3.14159)
t_init, t0, t1 = 0., 0.5, 1.
def ode_fn(t, x):
x, y = initial_population
return -(tf.math.cos(x) * tf.math.cos(y) *
tf.math.exp(-(x-pi)**2 - (y-pi)**2))
def gradients(x):
results = tfp.math.ode.BDF().solve(ode_fn, t_init, initial_population[0],
solution_times=[t0, t1])
return(results.states[0])
# The objective function and the gradient.
optim_results = tfp.optimizer.differential_evolution_minimize(
gradients,
initial_population=initial_population[0])
objective_value = optim_results[4]
DirSampleNoise = tfd.Dirichlet([tf.math.reduce_mean(objective_value), tf.math.reduce_std(objective_value)])
print(DirSampleNoise.sample([2,]))
# Check that the argmin is close to the actual value.
# Print out the total number of function evaluations it took. Should be 5.
Current, developments - can be found in this link - https://gitlab.com/emmanuelnsanga/bayes-distil-model/-/blob/main/optimizer_non-parametric.py
I was preparing some code for a lecture and re-implemented a simple perceptron: 2 inputs and 1 output. Aim: a linear classifier.
Here's the code that creates the data, setups the perceptron and trains it:
from ipywidgets import interact
import numpy as np
import matplotlib.pyplot as plt
# Two randoms clouds
x = [(1,3)]*10+[(3,1)]*10
x = np.asarray([(i+np.random.rand(), j+np.random.rand()) for i,j in x])
# Colors
cs = "m"*10+"b"*10
# classes
y = [0]*10+[1]*10
class Perceptron:
def __init__(self):
self.w = np.random.randn(3)
self.lr = 0.01
def train(self, x, y, verbose=False):
errs = 0.
for xi, yi in zip(x,y):
x_ = np.insert(xi, 0, 1)
r = self.w # x_
######## HERE IS THE MAGIC HAPPENING #####
r = r >= 0
##########################################
err = float(yi)-float(r)
errs += np.abs(err)
if verbose:
print(yi, r)
self.w = self.w + self.lr * err * x_
return errs
def predict(self, x):
return np.round(self.w # np.insert(x, 0, 1, 1).T)
def decisionLine(self):
w = self.w
slope = -(w[0]/w[2]) / (w[0]/w[1])
intercept = -w[0]/w[2]
return slope, intercept
p = Perceptron()
line_properties = []
errs = []
for i in range(20):
errs.append(p.train(x, y, True if i == 999 else False))
line_properties.append(p.decisionLine())
print(p.predict(x)) # works like a charm!
#interact
def showLine(i:(0,len(line_properties)-1,1)=0):
xs = np.linspace(1, 4)
a, b = line_properties[i]
ys = a * xs + b
plt.scatter(*x.T)
plt.plot(xs, ys, "k--")
At the end, I am calculating the decision boundary, i.e. the linear eq. separating class 0 and 1. However, it seems to be off. I tried inversion etc but have no clue what is wrong. Interestingly, if I change the learning rule to
self.w = self.w + self.lr * err / x_
i.e. dividing by x_, it works properly - I am totally confused. Anyone an idea?
Solved for real
Now I added one small, but very important part to the Perceptron that I just forgot (and maybe others may forget it as well). You have to do the thresholded activation! r = r >= 0 - and now it is centered on 0 and then it does work - this is basically the answer below. If you don't do this, you have to change the classes to get again the center at 0. Currently, I prefer having the classes -1 and 1 as this gives a better decision line (centered) instead of a line that is very close to one of the data clouds.
Before:
Now:
You are creating a linear regression (not logistic regression!) with targets 0 and 1. And the line you plot is the line where the model predicts 0, so it should ideally cut through the cloud of points labeled 0, as in your first plot.
If you don't want to implement the sigmoid for logistic regression, then at least you will want to display a boundary line that corresponds to a value of 0.5 rather than 0.
As for inverting the weights providing a plot that looks like what you want, I think that's just a coincidence of this data.
SOLUTION BELOW:
Scenario:
I am trying to compute the jacobian of a user defined function many, many times in a loop. I am able to do this with TF 2's GradientTape as well as the older session based tf.gradients() method. The problem is that GradientTape is terribly slow (100x slower) than tf.gradients(). It has features i'd like to use (bath_jacobian, hessian support, etc), but if it's 100x slower then i can't use it.
The Question:
It's not clear to me if i'm simply misusing GradientTape, or if it will always be slower because it has to re-differentiate the provided function every time its called (my suspicion). I'm asking for tips to fix my use of GradientTape or a confirmation that it will always be fundamentally slower than tf.gradients by orders of magnitude.
Related Questions:
Repeated use of GradientTape for multiple Jacobian calculations - same scenario, unanswered
Does `GradientTape` need to re-differentiate each evaluation of a derivative? - same scenario, unanswered
using one GradientTape with global context - loosely related, having trouble applyng that solution to my scenario
Fully contained minimum example to compare GradientTape and tf.gradients():
import tensorflow as tf
from tensorflow.python.framework.ops import disable_eager_execution
import numpy as np
# from tensorflow.python.ops.parallel_for.gradients import jacobian, batch_jacobian
import timeit
class FunctionCaller(object):
def __init__(self, func, nX, dtype=tf.float64, useSessions=True):
if useSessions:
disable_eager_execution()
self.func = func
self.nX = nX
self.useSessions = useSessions
self.dtype = dtype
self.sess = tf.compat.v1.Session() if useSessions else None
if not useSessions:
return
#
# we are in session mode, so build the graph and take the batch-jacobian of the function's outputs
#
xTensor = tf.compat.v1.placeholder(dtype, shape=[None, nX])
# add function to graph and guarantee its output shape
func_tensor = tf.reshape(func(xTensor), [-1, nX])
# take the gradient for each output, one at a time, and stack the results back together
each_output = tf.unstack(func_tensor, nX, axis=1)
jac_x = tf.stack([tf.gradients(output, xTensor, unconnected_gradients='zero')[0]
for output in each_output], axis=1)
# record these tensors so we can use them later with session.run()
self.xTensor = xTensor
self.func_tensor = func_tensor
self.jac_func_tensor = jac_x
def jac(self, x_i):
if self.useSessions:
return self.sess.run(self.jac_func_tensor, {self.xTensor: x_i})
else:
return self._useGradientTape(x_i)
# THIS FUNCTION IS SUPER INEFFICIENT.
def _useGradientTape(self, x_i):
with tf.GradientTape(persistent=True) as g:
xTensor = tf.Variable(x_i, dtype=self.dtype) # is this my problem??? i recreate x every time?
y = tf.reshape(self.func(xTensor), [-1, self.nX])
jac_x_at_i = g.batch_jacobian(y, xTensor)
# del g
return jac_x_at_i.numpy()
def __del__(self):
if self.sess is not None:
self.sess.close()
def main():
#tf.function
def Xdot(x_i):
x_0, x_1, x_2 = tf.split(x_i, 3, axis=1)
return tf.concat([x_2 * tf.sin(x_2), x_2 * tf.cos(x_2), x_2], axis=1)
nT = 20
nX = 3
# create some trash data
x_i = np.arange(nT*nX).reshape([-1, nX])
nTrials = 100
# try the eager version first
caller_eager = FunctionCaller(Xdot, nX, useSessions=False)
start_time = timeit.default_timer()
for _ in range(nTrials):
jac_eager = caller_eager.jac(x_i)
elapsed = timeit.default_timer() - start_time
print("eager code took {} sec: {} sec/trial".format(elapsed, elapsed/nTrials))
# now try the sessions version
caller_sessions = FunctionCaller(Xdot, nX, useSessions=True)
start_time = timeit.default_timer()
caller_sessions.jac(x_i) # call it once to do its graph building stuff?
for _ in range(nTrials):
jac_session = caller_sessions.jac(x_i)
elapsed = timeit.default_timer() - start_time
print("session code took {} sec: {} sec/trial".format(elapsed, elapsed/nTrials))
residual = np.max(np.abs(jac_eager - jac_session))
print('residual between eager and session trials is {}'.format(residual))
if __name__ == "__main__":
main()
EDIT - SOLUTION:
xdurch0 pointed out below that I should wrap _useGradientTape() in a #tf.function - something I was unsuccessful with before for other reasons. Once I did that, I had to move xTensor's definition outside the #tf.function wrapper by making it a member variable and using tf.assign().
With all this done, I find that GradientTape (for this simple example) is now on the same order of magnitude as tf.gradints. When running enough trials (~1E5), it's twice as fast as tf.gradients. awesome!
import tensorflow as tf
from tensorflow.python.framework.ops import disable_eager_execution
import numpy as np
import timeit
class FunctionCaller(object):
def __init__(self, func, nT, nX, dtype=tf.float64, useSessions=True):
if useSessions:
disable_eager_execution()
self.func = func
self.nX = nX
self.useSessions = useSessions
self.dtype = dtype
self.sess = tf.compat.v1.Session() if useSessions else None
if not useSessions:
# you should be able to create without an initial value, but tf is demanding one
# despite what the docs say. bug?
# tf.Variable(initial_value=None, shape=[None, nX], validate_shape=False, dtype=self.dtype)
self.xTensor = tf.Variable([[0]*nX]*nT, dtype=self.dtype) # x needs to be properly sized once
return
#
# we are in session mode, so build the graph and take the batch-jacobian of the function's outputs
#
xTensor = tf.compat.v1.placeholder(dtype, shape=[None, nX])
# add function to graph and guarantee its output shape
func_tensor = tf.reshape(func(xTensor), [-1, nX])
# take the gradient for each output, one at a time, and stack the results back together
each_output = tf.unstack(func_tensor, nX, axis=1)
jac_x = tf.stack([tf.gradients(output, xTensor, unconnected_gradients='zero')[0]
for output in each_output], axis=1)
# record these tensors so we can use them later with session.run()
self.xTensor = xTensor
self.func_tensor = func_tensor
self.jac_func_tensor = jac_x
def jac(self, x_i):
if self.useSessions:
return self.sess.run(self.jac_func_tensor, {self.xTensor: x_i})
else:
return self._useGradientTape(x_i).numpy()
#tf.function # THIS IS CRUCIAL
def _useGradientTape(self, x_i):
with tf.GradientTape(persistent=True) as g:
self.xTensor.assign(x_i) # you need to create the variable once outside the graph
y = tf.reshape(self.func(self.xTensor), [-1, self.nX])
jac_x_at_i = g.batch_jacobian(y, self.xTensor)
# del g
return jac_x_at_i
def __del__(self):
if self.sess is not None:
self.sess.close()
def main():
#tf.function
def Xdot(x_i):
x_0, x_1, x_2 = tf.split(x_i, 3, axis=1)
return tf.concat([x_2 * tf.sin(x_2), x_2 * tf.cos(x_2), x_2], axis=1)
nT = 20
nX = 3
# create some trash data
x_i = np.random.random([nT, nX])
nTrials = 1000 # i find that nTrials<=1E3, eager is slower, it's faster for >=1E4, it's TWICE as fast for >=1E5
# try the eager version first
caller_eager = FunctionCaller(Xdot, nT, nX, useSessions=False)
start_time = timeit.default_timer()
for _ in range(nTrials):
jac_eager = caller_eager.jac(x_i)
elapsed = timeit.default_timer() - start_time
print("eager code took {} sec: {} sec/trial".format(elapsed, elapsed/nTrials))
# now try the sessions version
caller_sessions = FunctionCaller(Xdot, nT, nX, useSessions=True)
start_time = timeit.default_timer()
for _ in range(nTrials):
jac_session = caller_sessions.jac(x_i)
elapsed = timeit.default_timer() - start_time
print("session code took {} sec: {} sec/trial".format(elapsed, elapsed/nTrials))
residual = np.max(np.abs(jac_eager - jac_session))
print('residual between eager and session trials is {}'.format(residual))
if __name__ == "__main__":
main()
I would like to use tensorflow (version 2) to use gaussian process regression
to fit some data and I found the google colab example online here [1].
I have turned some of this notebook into a minimal example that is below.
Sometimes the code fails with the following error when using MCMC to marginalize the hyperparameters: and I was wondering if anyone has seen this before or knows how to get around this?
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input matrix is not invertible.
[[{{node mcmc_sample_chain/trace_scan/while/body/_168/smart_for_loop/while/body/_842/dual_averaging_step_size_adaptation___init__/_one_step/transformed_kernel_one_step/mh_one_step/hmc_kernel_one_step/leapfrog_integrate/while/body/_1244/leapfrog_integrate_one_step/maybe_call_fn_and_grads/value_and_gradients/value_and_gradient/gradients/leapfrog_integrate_one_step/maybe_call_fn_and_grads/value_and_gradients/value_and_gradient/PartitionedCall_grad/PartitionedCall/gradients/JointDistributionNamed/log_prob/JointDistributionNamed_log_prob_GaussianProcess/log_prob/JointDistributionNamed_log_prob_GaussianProcess/get_marginal_distribution/Cholesky_grad/MatrixTriangularSolve}}]] [Op:__inference_do_sampling_113645]
Function call stack:
do_sampling
[1] https://colab.research.google.com/github/tensorflow/probability/blob/master/tensorflow_probability/examples/jupyter_notebooks/Gaussian_Process_Regression_In_TFP.ipynb#scrollTo=jw-_1yC50xaM
Note that some of code below is a bit redundant but it should
in some sections but it should be able to reproduce the error.
Thanks!
import time
import numpy as np
import tensorflow.compat.v2 as tf
import tensorflow_probability as tfp
tfb = tfp.bijectors
tfd = tfp.distributions
tfk = tfp.math.psd_kernels
tf.enable_v2_behavior()
import matplotlib
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
#%pylab inline
# Configure plot defaults
plt.rcParams['axes.facecolor'] = 'white'
plt.rcParams['grid.color'] = '#666666'
#%config InlineBackend.figure_format = 'png'
def sinusoid(x):
return np.sin(3 * np.pi * x[..., 0])
def generate_1d_data(num_training_points, observation_noise_variance):
"""Generate noisy sinusoidal observations at a random set of points.
Returns:
observation_index_points, observations
"""
index_points_ = np.random.uniform(-1., 1., (num_training_points, 1))
index_points_ = index_points_.astype(np.float64)
# y = f(x) + noise
observations_ = (sinusoid(index_points_) +
np.random.normal(loc=0,
scale=np.sqrt(observation_noise_variance),
size=(num_training_points)))
return index_points_, observations_
# Generate training data with a known noise level (we'll later try to recover
# this value from the data).
NUM_TRAINING_POINTS = 100
observation_index_points_, observations_ = generate_1d_data(
num_training_points=NUM_TRAINING_POINTS,
observation_noise_variance=.1)
def build_gp(amplitude, length_scale, observation_noise_variance):
"""Defines the conditional dist. of GP outputs, given kernel parameters."""
# Create the covariance kernel, which will be shared between the prior (which we
# use for maximum likelihood training) and the posterior (which we use for
# posterior predictive sampling)
kernel = tfk.ExponentiatedQuadratic(amplitude, length_scale)
# Create the GP prior distribution, which we will use to train the model
# parameters.
return tfd.GaussianProcess(
kernel=kernel,
index_points=observation_index_points_,
observation_noise_variance=observation_noise_variance)
gp_joint_model = tfd.JointDistributionNamed({
'amplitude': tfd.LogNormal(loc=0., scale=np.float64(1.)),
'length_scale': tfd.LogNormal(loc=0., scale=np.float64(1.)),
'observation_noise_variance': tfd.LogNormal(loc=0., scale=np.float64(1.)),
'observations': build_gp,
})
x = gp_joint_model.sample()
lp = gp_joint_model.log_prob(x)
print("sampled {}".format(x))
print("log_prob of sample: {}".format(lp))
# Create the trainable model parameters, which we'll subsequently optimize.
# Note that we constrain them to be strictly positive.
constrain_positive = tfb.Shift(np.finfo(np.float64).tiny)(tfb.Exp())
amplitude_var = tfp.util.TransformedVariable(
initial_value=1.,
bijector=constrain_positive,
name='amplitude',
dtype=np.float64)
length_scale_var = tfp.util.TransformedVariable(
initial_value=1.,
bijector=constrain_positive,
name='length_scale',
dtype=np.float64)
observation_noise_variance_var = tfp.util.TransformedVariable(
initial_value=1.,
bijector=constrain_positive,
name='observation_noise_variance_var',
dtype=np.float64)
trainable_variables = [v.trainable_variables[0] for v in
[amplitude_var,
length_scale_var,
observation_noise_variance_var]]
# Use `tf.function` to trace the loss for more efficient evaluation.
#tf.function(autograph=False, experimental_compile=False)
def target_log_prob(amplitude, length_scale, observation_noise_variance):
return gp_joint_model.log_prob({
'amplitude': amplitude,
'length_scale': length_scale,
'observation_noise_variance': observation_noise_variance,
'observations': observations_
})
# Now we optimize the model parameters.
num_iters = 1000
optimizer = tf.optimizers.Adam(learning_rate=.01)
# Store the likelihood values during training, so we can plot the progress
lls_ = np.zeros(num_iters, np.float64)
for i in range(num_iters):
with tf.GradientTape() as tape:
loss = -target_log_prob(amplitude_var, length_scale_var,
observation_noise_variance_var)
grads = tape.gradient(loss, trainable_variables)
optimizer.apply_gradients(zip(grads, trainable_variables))
lls_[i] = loss
print('Trained parameters:')
print('amplitude: {}'.format(amplitude_var._value().numpy()))
print('length_scale: {}'.format(length_scale_var._value().numpy()))
print('observation_noise_variance: {}'.format(observation_noise_variance_var._value().numpy()))
num_results = 100
num_burnin_steps = 50
sampler = tfp.mcmc.TransformedTransitionKernel(
tfp.mcmc.HamiltonianMonteCarlo(
target_log_prob_fn=target_log_prob,
step_size=tf.cast(0.1, tf.float64),
num_leapfrog_steps=8),
bijector=[constrain_positive, constrain_positive, constrain_positive])
adaptive_sampler = tfp.mcmc.DualAveragingStepSizeAdaptation(
inner_kernel=sampler,
num_adaptation_steps=int(0.8 * num_burnin_steps),
target_accept_prob=tf.cast(0.75, tf.float64))
initial_state = [tf.cast(x, tf.float64) for x in [1., 1., 1.]]
# Speed up sampling by tracing with `tf.function`.
#tf.function(autograph=False, experimental_compile=False)
def do_sampling():
return tfp.mcmc.sample_chain(
kernel=adaptive_sampler,
current_state=initial_state,
num_results=num_results,
num_burnin_steps=num_burnin_steps,
trace_fn=lambda current_state, kernel_results: kernel_results)
t0 = time.time()
samples, kernel_results = do_sampling()
t1 = time.time()
print("Inference ran in {:.2f}s.".format(t1-t0))
This can happen if you have multiple index points that are very close, so you might consider using np.linspace or just doing some post filtering of your random draw. I would also suggest a bit bigger epsilon, maybe 1e-6.
I am trying to implement the 'Iterative hessian Sketch' algorithm from https://arxiv.org/abs/1411.0347 page 12. However, I am struggling with step two which needs to minimize the matrix-vector function.
Imports and basic data generating function
import numpy as np
import scipy as sp
from sklearn.datasets import make_regression
from scipy.optimize import minimize
import matplotlib.pyplot as plt
%matplotlib inline
from numpy.linalg import norm
def generate_data(nsamples, nfeatures, variance=1):
'''Generates a data matrix of size (nsamples, nfeatures)
which defines a linear relationship on the variables.'''
X, y = make_regression(n_samples=nsamples, n_features=nfeatures,\
n_informative=nfeatures,noise=variance)
X[:,0] = np.ones(shape=(nsamples)) # add bias terms
return X, y
To minimize the matrix-vector function, I have tried implementing a function which computes the quanity I would like to minimise:
def f2min(x, data, target, offset):
A = data
S = np.eye(A.shape[0])
#S = gaussian_sketch(nrows=A.shape[0]//2, ncols=A.shape[0] )
y = target
xt = np.ravel(offset)
norm_val = (1/2*S.shape[0])*norm(S#A#(x-xt))**2
#inner_prod = (y - A#xt).T#A#x
return norm_val - inner_prod
I would eventually like to replace S with some random matrices which can reduce the dimensionality of the problem, however, first I need to be confident that this optimisation method is working.
def grad_f2min(x, data, target, offset):
A = data
y = target
S = np.eye(A.shape[0])
xt = np.ravel(offset)
S_A = S#A
grad = (1/S.shape[0])*S_A.T#S_A#(x-xt) - A.T#(y-A#xt)
return grad
x0 = np.zeros((X.shape[0],1))
xt = np.zeros((2,1))
x_new = np.zeros((2,1))
for it in range(1):
result = minimize(f2min, x0=xt,args=(X,y,x_new),
method='CG', jac=False )
print(result)
x_new = result.x
I don't think that this loop is correct at all because at the very least there should be some local convergence before moving on to the next step. The output is:
fun: 0.0
jac: array([ 0.00745058, 0.00774882])
message: 'Desired error not necessarily achieved due to precision loss.'
nfev: 416
nit: 0
njev: 101
status: 2
success: False
x: array([ 0., 0.])
Does anyone have an idea if:
(1) Why I'm not achieving convergence at each step
(2) I can implement step 2 in a better way?