I want to run a code via pylearn2 with Theano backbone. updates is a OrderedDict and the most of the its values are float64 type meanwhile two of them are float32. When I want to run a code and it reaches to this line
train_fn = theano.function([input, target, LR], loss, updates=updates)
this error arisen.
Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/theano/compile/pfunc.py", line 192, in rebuild_collect_shared
update_val = store_into.type.filter_variable(update_val,
File "/usr/local/lib/python3.9/site-packages/theano/tensor/type.py", line 229, in filter_variable
raise TypeError(
TypeError: Cannot convert Type TensorType(float64, matrix) (of Variable Elemwise{add,no_inplace}.0) into Type TensorType(float32, matrix).
You can try to manually convert Elemwise{add,no_inplace}.0 into a TensorType(float32, matrix).
It suggests to convert manually.
Related
I am using PyTorch version 1.5.0.
When I pass an input torch tensor of size [8,21,400,400] with a target of size [8,400,400], the program raises a TypeError: iteration over a 0-d tensor. However, the dimensions of the arguments are 4 and 3 respectively.
What could be causing this error?
The traceback points to torch\tensor.py's iter function.
Traceback (most recent call last):
File "train.py", line 108, in <module>
loss, accuracy = lossLayer(pred2, targetBatch)
File "C:\Users\PC\anaconda3\lib\site-packages\torch\tensor.py", line 462, in __iter__
raise TypeError('iteration over a 0-d tensor')
TypeError: iteration over a 0-d tensor
You get the error because nn.CrossEntropyLoss just returns one torch.Tensor, not a pair (it doesn't return accuracy). And this tensor is 0-dimensional, i.e. one number (unless you don't override reduction argument to 'none' to get per-element loss). So when you try to assign its value to two variables loss, accuracy python tries to iterate over this tensor variable, hence the error message. Simply use loss = lossLayer(pred2, targetBatch).
Traceback (most recent call last):
File "C:/Users/Lenovo/PycharmProjects/ProjetFinal/venv/turkish.py", line 45, in <module>
sequences_matrix = sequence.pad_sequences(sequences,maxlen=max_len)
File "C:\Users\Lenovo\PycharmProjects\ProjetFinal\venv\lib\site-packages\keras_preprocessing\sequence.py", line 96, in pad_sequences
trunc = np.asarray(trunc, dtype=dtype)
File "C:\Users\Lenovo\PycharmProjects\ProjetFinal\venv\lib\site-packages\numpy\core\_asarray.py", line 85, in asarray
return array(a, dtype, copy=False, order=order)
ValueError: invalid literal for int() with base 10:
windows loading yapıo sonra mavi ekran iste. simdi repair yapıyo bkalım olmazsa
gelirim size.
X = dft.text
your straight using text with pad_sequence. this is how pad_sequence doesn't work
Generally, every text is converted into numbers within a given vocab which can be of characters or words depend upon task.
then it can be padded.
please refer some tutorial through you can understand how to process text first.
Tensorflow tutorials - text part are good to start.
https://www.tensorflow.org/guide/keras/masking_and_padding
I am getting the following error in the terminal:
Traceback (most recent call last):
File "deep_Q_learner.py", line 289, in <module>
agent.replay_experience()
File "deep_Q_learner.py", line 170, in replay_experience
self.learn_from_batch_experience(experience_batch)
File "deep_Q_learner.py", line 151, in learn_from_batch_experience
self.Q_target(next_obs_batch).max(1)[0].data
TypeError: mul(): argument 'other' (position 1) must be Tensor, not numpy.ndarray
The link to the code is:
https://github.com/PacktPublishing/Hands-On-Intelligent-Agents-with-OpenAI-Gym/blob/master/ch6/deep_Q_learner.py
The error is seen only when self.DQN=SLP (see line#76)
Is there a fix to this issue? Am I missing something here?
As the error suggests, you are supposed to pass in a torch.tensor object, where you are passing a numpy array object. Convert your numpy array to torch.tenosr by:
new_torch_tensor = torch.tensor(numpy_array)
I am stuck in a simple looking problem in Tensorflow.
Traceback (most recent call last):
File op_def_library.py, line 510, in _apply_op_helper
preferred_dtype=default_dtype)
File ops.py, line 1040, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File ops.py, line 883, in _TensorTensorConversionFunction
(dtype.name, t.dtype.name, str(t)))
ValueError: Tensor conversion requested dtype int64 for Tensor with dtype float32: 'Tensor("sequence_sparse_softmax_cross_entropy/zeros_like:0", shape=(?, ?, 10004), dtype=float32)'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "red.py", line 281, in <module>
main()
File "red.py", line 99, in main
sequence_length=lengths)
File loss.py, line 225, in sequence_sparse_softmax_cross_entropy
losses = xloss(labels=labels, logits=logits)
File loss.py", line 48, in loss
post = array_ops.where(target_tensor > zeros, target_tensor - sigmoid_p, zeros)
gen_math_ops.py, line 2924, in greater
"Greater", x=x, y=y, name=name)
op_def_library.py, line 546, in _apply_op_helper
inferred_from[input_arg.type_attr]))
TypeError: Input 'y' of 'Greater' Op has type float32 that does not match type int64 of argument 'x'
Using as type also does not work.
I just defined another function to be used. I defined it and tried to use it. What should I do to make it work? I just want to define a function that takes tensors as input just like tf cross entropy function. Please suggest how to do that.
In particular, how can I resolve the error?
I have seen problems similar to mine here on Stack Overflow, but not exactly the same. I can reshape when using fully-connected NN layers, but not with Conv1D layers. Here's a minimal example. I'm using TF 1.4.0 on Python 3.6.3.
import tensorflow as tf
# fully connected
fc = tf.placeholder(tf.float32, [None,12])
fc = tf.contrib.layers.fully_connected(fc, 12)
fc = tf.contrib.layers.fully_connected(fc, 6)
fc = tf.reshape(fc, [-1,3,2])
# convolutional
con = tf.placeholder(tf.float32, [None,50,4])
con = tf.layers.Conv1D(con, 12, 3, activation=tf.nn.relu)
con = tf.layers.Conv1D(con, 6, 3, activation=tf.nn.relu)
con = tf.reshape(con, [-1,50,3,2])
Here is the output (yes, I'm aware of the RuntimeWarning. The messages I have found which discuss it suggest that it's harmless, but if you know otherwise, please share!):
/usr/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
return f(*args, **kwds)
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in make_tensor_proto
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_util.py", line 468, in <listcomp>
str_values = [compat.as_bytes(x) for x in proto_values]
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/compat.py", line 65, in as_bytes
(bytes_or_text,))
TypeError: Expected binary or unicode string, got <tensorflow.python.layers.convolutional.Conv1D object at 0x7fa67e0d1a20>
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "minimal reshape example.py", line 16, in <module>
con = tf.reshape(con, [-1,width,3,2])
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 3938, in reshape
"Reshape", tensor=tensor, shape=shape, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 513, in _apply_op_helper
raise err
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 510, in _apply_op_helper
preferred_dtype=default_dtype)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 926, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py", line 229, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/constant_op.py", line 208, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_util.py", line 472, in make_tensor_proto
"supported type." % (type(values), values))
TypeError: Failed to convert object of type <class 'tensorflow.python.layers.convolutional.Conv1D'> to Tensor. Contents: <tensorflow.python.layers.convolutional.Conv1D object at 0x7fa67e0d1a20>. Consider casting elements to a supported type.
My code fails at con = tf.reshape(con, [-1,50,3,2]). Yet the pattern is nearly identical to the pattern that I use for the fully-connected graph, fc.
I made nets very similar to these work in the higher-level API for TensorFlow called TFLearn. However, TFLearn's DNN Estimator object is having trouble managing a tf.Session correctly. After over a month, I have yet to resolve the issue with TFLearn's developers on GitHub.
I don't mind using TensorFlow's native Estimator, but I have to solve this reshape problem to achieve it.
Well, I found the error: tf.layers.Conv1D != tf.layers.conv1d. Changing the former to the latter eliminated the error. Let the TensorFlow / Python user beware!
Even though TensorFlow seems to avoid Python's object model (which is probably necessary, given the possibility of distributed, low-level computation), there are in fact a few genuine classes in the Python API. The class constructors can accept many (all?) of the same arguments as the similarly-named convenience functions.