I'm having a tough time using the 'initial state' argument in the tf.nn.rnn function.
val, _ = tf.nn.rnn(cell1, newBatch, initial_state=stateP, dtype=tf.float32)
newBatch.shape => (1, 1, 11)
stateP.shape => (2, 2, 1, 11)
In general, I've gone through the training for my LSTM neural net and now I want to use the values of it. How do I do this? I know that the tf.nn.rnn() function will return state... but I don't know how to plug it in.
fyi stateP.shape => (2, 2, 1, 11) ..... maybe because I used stacked LSTM cells?
I've also tried:
val, _ = tf.nn.dynamic_rnn(stacked_lstm, newBatch, initial_state=stateP, dtype=tf.float32)
but I get the error "AttributeError: 'NoneType' object has no attribute 'op'".
I'm pretty sure that the 'NoneType' object being talked about is the stateP tuple I gave, but I'm not sure what to do here.
EDIT: I finally got this running by using:
init_state = cell.zero_state(batch_size, tf.float32)
To determine the exact shape I need to pass into the 'initial_state' argument. In my case, it was a TUPLE of 4 tensors, each with the shape of (1, 11). I made it like this:
stateP0 = tf.convert_to_tensor(stateP[0][0])
stateP1 = tf.convert_to_tensor(stateP[0][1])
stateP2 = tf.convert_to_tensor(stateP[1][0])
stateP3 = tf.convert_to_tensor(stateP[1][1])
newStateP = stateP0, stateP1, stateP2, stateP3
Alright! Now the tf.dynamic_rnn() function is working, but it's giving me different results every time I run it.... so what's the point of passing in the initial state? I want to use the state I trained to find... and I don't want it to change. I want to actually use the results of my training!
You are probably using the deprecated (or soon to be) behavior. stateP in your case represents the concatenation of c (cell state) and h (output of lstm from the final step of unrolling). So you need to slice the state along dimension 1 to get the actual state.
Or, you can initialize your LSTM cell with state_is_tuple=True, which I would recommend, so that you could easily get the final state (if you want to tinker with it) by indexing the state stateP[0]. Or you could just pass the state tuple directly to rnn (or dynamic_rnn).
I cant say anything beyond that because you have not provided your initialization code. So I would be guessing.
You can edit your question to provide more details if you still face problems and I would edit the answer.
Related
Goal: I want to train a PPO agent on a problem and determine its optimal value function for a range of observations. Later I plan to work with this value function (economic inequality research). The problem is sufficiently complex so that dynamic programming techniques no longer work.
Approach: In order to check, whether I get correct outputs for the value function, I have trained PPO on a simple problem, whose analytical solution is known. However, the results for the value function are rubbish, which is why I suspect that I have done sth wrong.
The code:
from keras import backend as k_util
...
parser = argparse.ArgumentParser()
# Define framework to use
parser.add_argument(
"--framework",
choices=["tf", "tf2", "tfe", "torch"],
default="tf",
help="The DL framework specifier.",
)
...
def get_rllib_config(seeds, debug=False, framework="tf") -> Dict:
...
def get_value_function(agent, min_state, max_state):
policy = agent.get_policy()
value_function = []
for i in np.arange(min_state, max_state, 1):
model_out, _ = policy.model({"obs": np.array([[i]], dtype=np.float32)})
value = k_util.eval(policy.model.value_function())[0]
value_function.append(value)
print(i, value)
return value_function
def train_schedule(config, reporter):
rllib_config = config["config"]
iterations = rllib_config.pop("training_iteration", 10)
agent = PPOTrainer(env=rllib_config["env"], config=rllib_config)
for _ in range(iterations):
result = agent.train()
reporter(**result)
values = get_value_function(agent, 0, 100)
print(values)
agent.stop()
...
resources = PPO.default_resource_request(exp_config)
tune_analysis = tune.Tuner(tune.with_resources(train_schedule, resources=resources), param_space=exp_config).fit()
ray.shutdown()
So first I get the policy (policy = agent.get_policy()) and run a forward pass with each of the 100 values (model_out, _ = policy.model({"obs": np.array([[i]], dtype=np.float32)})). Then, after each forward pass I use the value_function() method to get the output of the critic network and evaluate the tensor via keras backend.
The results:
True VF (analytical solution)
VF output of Rllib
Unfortunately you can see that the results are not that promising. Maybe I have missed a pre- or postprocessing step? Does the value_function() method even return the last layer of the critic network?
I am very grateful for any help!
It's not part of your script, but I assume that you have trained the policy before you attempt to get useful values out of it.
You are correct in assuming that the value_function() returns the output of the last layer of the critic network in RLlib's implementations.
Have a look at the value function metrics to see if it's actually learning anything (RLlib logs .../learner_stats/vf_loss and .../learner_stats/vf_explained_var)!
After training the model, I'd also try to query the model directly. If that looks better, something is likely off with the code you posted here.
I have the following code:
shape = tf.shape(tensor, out_type=tf.int64, name='sparse_shape')
nelems = tf.size(tensor, out_type=tf.int64, name='num_elements')
indices = tf.transpose(
tf.unravel_index(tf.range(nelems, dtype=tf.int64), shape),
name='sparse_indices')
values = tf.reshape(tensor, [nelems], name='sparse_values')
This code snippet is simply transforming a dense tensor into a sparse tensor. However I found that the reshape op sometimes raises an error in runtime:
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 906 values, but the requested shape has 1024
It's hard to write a simple demo to reproduce this bad case. So please understand that I cannot provide a reproducible demo.
But notice that my code is very simple. The reshape op is simply reshaping the tensor into a 1D tensor with the dimension size as the tensor's size, which is the number of elements of the tensor (illustrated in TensorFlow's doc). And in my mind, the number of elements here simply means the number of of values in the error message. Thus the above error should never appear.
I tried to use production of the shape as the target dimension size instead of tf.size but it was no use:
shape = tf.shape(tensor, out_type=tf.int64, name='sparse_shape')
# use production as the number of elements
nelems = tf.reduce_prod(shape, name='num_elements')
....
values = tf.reshape(tensor, [nelems], name='sparse_values')
So my question is, why is there a possibility that, for a certain tensor tensor, tf.size(tensor) or tf.shape(tensor) does not tell the actual number of elements of tensor? Can anyone remind if I have missed anything? Thanks.
I have figured out the problem on myself.
Problem:
In my project, the problem is that, tensor is produced by a third-party library. The library called tensor.set_shape([1024]) before returning tensor. While it can't ensure that there must be 1024 elements in tensor.
According to these codes, in TensorFlow's python frontend implementation, when the shape is fully determined, tf.shape and tf.size can go a fast way to get the result without really running the ShapeOp or SizeOp, and returning a constant tensor of the determined shape dimensions as the result.
As a result, in my case, the shape is obviously fully determined as [1024], so the code goes in the fast way and returned tf.constant([1024]). However the real shape of the Tensor object in the backend is [906].
Solution
According to the previously mentioned codes, we can see that tf.shape and tf.size actually calls shape_internal and size_internal defined in tensorflow.python.ops.array_ops. The latter functions takes one more argument optimize with default value True. And if optimize is false, the fast way will be ignored.
So the solution is to replace the tf.shape or tf.size with shape_internal or size_internal, and pass optimize=False.
# internal functions are not exposed by `tensorflow` root package
# so we have to import the `array_ops` package manualy
from tensorflow.python.ops import array_ops
....
shape = tf.shape(tensor, out_type=tf.int64, name='sparse_shape')
#nelems = tf.size(tensor, out_type=tf.int64, name='num_elements')
nelems = array_ops.size_internal(tensor, optimize=False, out_type=tf.int64, name='num_elements')
....
values = tf.reshape(tensor, [nelems], name='sparse_values')
I cannot see the difference between what I am doing and the working Google TFP example, whose structure I am following. What am I doing wrong/should I be doing differently?
[Setup: Win 10 Home 64-bit 20H2, Python 3.7, TF2.4.1, TFP 0.12.2, running in Jupyter Lab]
I have been building a model step by step following the example of TFP Probabilistic Layers Regression. The Case 1 code runs fine, but my parallel model doesn't and I cannot see the difference that might cause this
yhat = model(x_tst)
to fail with message Input 0 of layer sequential_14 is incompatible with the layer: : expected min_ndim=2, found ndim=1. Full shape received: (2019,) (which is the correct 1D size of x_tst)
For comparison: Google's load_dataset function for the TFP example returns y, x, x_tst, which are all np.ndarray of size 150, whereas I read data from a csv file with pandas.read_csv, split it into train_ and test_datasets and then take 1 col of data as independent variable 'g' and dependent variable 'redz' from the training dataset.
I know x, y, etc. need to be np.ndarray, but one does not create ndarray directly, so I have...
x = np.array(train_dataset['g'])
y = np.array(train_dataset['redz'])
x_tst = np.array(test_dataset['g'])
where x, y, x_tst are all 1-dimensional - just like the TFP example.
The model itself runs
model = tf.keras.Sequential([
tf.keras.layers.Dense(1),
tfp.layers.DistributionLambda(lambda t: tfd.Normal(loc=t, scale=1)),
])
# Do inference.
model.compile(optimizer=tf.optimizers.Adam(learning_rate=0.01), loss=negloglik)
model.fit(x, y, epochs=1, verbose=False);
(and when plotted gives the expected output for the google data - I don't get this far):
But, per the example when I try to "profit" by doing yhat = model(x_tst) I get the dimensions error given above.
What's wrong?
(If I try mode.predict I think I hit a known bug/gap in TFP; then it fails the assert)
Update - Explicit Reshape Resolves Issue
The hint from Frightera led to further investigation: x_tst had shape (2019,)
Reshaping by x_tst = x_tst.rehape(2019,1) resolved the issue. Is TF inconsistent in its requirements or is there some good reason that the explicit final dimension 1 was required? Who knows. At least predictions can be made now.
In this question Difference between numpy.array shape (R, 1) and (R,), the OP asked for the difference between (R,) and (R,1) but the answers given did not address this specific point.
Similarly in this question Difference between these array shapes in numpy
I believe the answer lies in the numpy glossary, where it says of (n,) that
A parenthesized number followed by a comma denotes a tuple with one
element. The trailing comma distinguishes a one-element tuple from a
parenthesized n.
Which, naturally, echoes the Python statements concerning tuples here
Thus an array of shape (R,) is a tuple describing an array as being 1D of a certain extent R, where the comma is appended to distinguish the tuple (R,) from the non-tuple (R).
However, for a 1D array, there is no sense of row or column ordering; (R,1) is R rows by 1 column, but (1, R) would be 1 row of R columns, and though it shouldn't matter to a 1D iterator either it does or the iterator doesn't correctly recognise ( ,) and thinks it is 2D. (i.e. I don't know the technical details of that part, but these seem to be the only options that account for the behaviour.)
This issue is unrelated to the indeterminacy of size that occurs in tensor definition in Tensorflow. In the context of Tensorflow, Tensors (arrays) may have indeterminate shapes, so that more data may be added along a certain axis as processing occurs, e.g. in batches, in which case the initial Tensor shape includes a leading None to indicate where array expansion is expected to occur. (See e.g. tensor's shape here)
Suppose I have a matrix of N users, and each user is associated with a vector of words (translated to integers). So for example for N = 2 I'd have:
user 0 corresponds to words['20','56']
user 1 corresponds to words ['58','10','105']
So I have a list
user_words = [['20','56'],['58','10','105']]
Suppose further I created a 100-column embedding matrix (word_emb) for these words. I'd like to look up the (mean) embeddings of each of the user vectors and create a new Tensor, whose shape I would expect to be [2,100]. I tried doing this:
word_vec = []
for word_sequence_i in tf.map_fn(lambda x: x, user_words):
all_word_vecs = tf.nn.embedding_lookup(word_emb, word_sequence_i)
word_vec.append( tf.reduce_mean(all_word_vecs, 1))
But this gives me an error:
TypeError: `Tensor` objects are not iterable when eager execution is not enabled. To iterate over this tensor use `tf.map_fn`.
I thought I already was using tf.map_fn above! So what is Tensorflow complaining about? Is there even a way to do what I am trying to do?
Thanks so much!
tf.map_fn returns a Tensor object itself, which is a symbolic reference to a value that will be computed at Session.run() time. You can see this with type(tf.map_fn(lambda x: x, user_words)). So, it's the iteration implied in for word_sequence_i in tf.map_fn(...) that is generating the error.
Perhaps what you're looking for is something like:
all_word_vecs = tf.map_fn(lambda x: tf.nn.embedding_lookup(word_emb, x), user_words)
word_vec = tf.reduce_mean(all_word_vecs, axis=1)
On a related note, if this distinction between graph construction and execution is getting bothersome, you might want to give TensorFlow's eager execution a spin. See getting started and the programmer's guide.
Hope that helps.
I am trying to solve the following linear system using optimize.root
AX = b
With the following code.
A = [[0,1,0],[2,1,0],[1,4,1]]
def foo(X):
b = np.matrix([2,1,1])
out = np.dot(A,X) - b
return out.tolist()
sol = scipy.optimize.root(foo,[0,0,0])
I know that I can simply use the numpy.linalg.solve to do this easily. But I am actually trying to solve a non linear system that is in matrix form. See my question here. So I need to find a way to make this method work. To do that I am trying to solve this problem in this simple case. But I get the error
TypeError: fsolve: there is a mismatch between the input and output shape of the 'func' argument 'foo'.Shape should be (3,) but it is (1, 3).
From what I have read from other similar stackoverflow questions this happens because the out put of the foo function is not compatible with the shape of the initial guess [0,0,0]
Surely there is a way to solve this equation using scipy.optimize.root. Can anyone please help?
(I'm assuming the capital B in your .dot is a typo for A.)
Try using np.array for b. np.matrix creates a "row vector", i.e. shape (1, 3) whereas your initial guess has shape (3,).