Feb 13, 2019 · AttributeError: 'Tensor' object has no attribute 'numpy' in image_captioning_with_attention.ipynb #25731 DecentGradient opened this issue Feb 13, 2019 · 9 comments Assignees
12.07.2019 · The issue tracker should only be used to report bugs or feature requests. If you are looking for support from other library users, please ask a question on StackOverflow. Hi, I am trying to train a DQN model based on RL-attack examples u...
Here is the full code. This currently works just fine on my M1 MacBook running Monterey and Tensorflow-Metal. However, when I export the dataset and code to my laptop with an RTX 3060 Laptop GPU with Pop_OS! that is when I start getting the [UNK] characters generated and "NaN" loss.
The output of tf.nn.softmax_cross_entropy_with_logits on a shape [2,5] tensor is of shape ... in <module> AttributeError: "MyNT" object has no attribute "quux"
AttributeError: 'list' object has no attribute 'size' with HuggingFace model ... input_ids object into pt (PyTorch Tensors), tf (TensorFlow Tensors) or np ...
Mar 06, 2021 · I got the error: AttributeError: 'NoneType' object has no attribute 'logits' I'm wondering where my code applying tutorial is wrong so that model can't be created. Addition Information
Aug 28, 2021 · Hi everyone, I am training an RNN and have come across the following error 247 input = cast(Tensor, input) 248 batch_sizes = None -->; 249 max_batch_size = input.size ...
24.01.2020 · System information Have I written custom code (as opposed to using a stock example script provided in TensorFlow): Yes OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Mac OS Catalina (Version: 10.15.2 (19C57)) TensorFlow install...
Dec 09, 2021 · Show activity on this post. I am trying to train a neural network to do multiclass classification on each character of supplied text. This is the code I am using: xtrain = tf.ragged.constant (list (training ['encoded_text']), dtype=tf.int64) ytrain = tf.ragged.constant (list (training ['labels']), dtype=tf.bool) model = tf.keras.Sequential ...
In this setting there is no need to use variable sharing since the variables are kept as attributes of the model object. Also, after calling the training ...
13.03.2019 · 1 Answer1. Show activity on this post. the row rewards.append (reward) causes the error, an it is because your rewards variable is a Tensor, as you defined it in rewards = tf.placeholder ('float32',shape= [None]) and you can not append values to tensor like that. You probably wanted to call rewards_list.append (reward).