All Questions

Tagged with
Filter by
Sorted by
Tagged with
-1votes
0answers
10views

Ragged nested array need to be converted to array of float

I have a ragged nested array with class 'numpy.ndarray' which I want to convert it to a string of float which I already try to use np.asfarray to change it. the problem is that, my Jupyter Notebook ...
user avatar
0votes
0answers
6views

My tensorflow object detection model produced the average precision of zero for first class

I have trained the object detection model for three classes: id=1 (LR), id=2 (PM), id=3 (YR). Model produced AP(LR):0.002, PM:0.84,YR:1.00 and after that changed id=1 (YR), id=2(PM), id=3(YR). Model ...
user avatar
0votes
0answers
20views

No camera detection in Python3 TensorFlow

I am trying to do a run using TensorFlow in python for image recognition. Everything seems correct but when I run the camera it tells me that it does not detect it, displaying the error message in the ...
user avatar
  • 1
0votes
0answers
25views

ModuleNotFoundError: No module named 'keras.layers.preprocessing'

After writing this - VERIFICATION_SCRIPT = os.path.join(paths['APIMODEL_PATH'], 'research', 'object_detection', 'builders', 'model_builder_tf2_test.py') !python {VERIFICATION_SCRIPT} I am getting this ...
user avatar
  • 5
0votes
0answers
11views

Inconsistent tensorflow model.predict() error INVALID_ARGUMENT: padded_shape[1]=106 is not divisible by block_shape[1]=6

After around 3 iterations, the code below produces the error: W tensorflow/core/framework/op_kernel.cc:1745] OP_REQUIRES failed at spacetobatch_op.cc:219 : INVALID_ARGUMENT: padded_shape[1]=106 is ...
user avatar
  • 11
0votes
0answers
22views

Tensorflow: Shape must be at least rank 3 but is rank 2

I am training a bilstm model for text classification and running into the following error ValueError: Shape must be at least rank 3 but is rank 2 for '{{node bidirectional_5/forward_lstm_6/...
user avatar
  • 6,928
-2votes
1answer
25views

ModuleNotFoundError: No module named 'hcaptcha'

I am trying to execute a code of mine, but i keep getting the following error: ModuleNotFoundError: No module named 'hcaptcha' When I try installing 'hcaptcha' from pip install hcaptcha, it say this:...
user avatar
-1votes
0answers
53views

AttributeError: 'bool' object has no attribute 'op'

I'm a beginner in python. I'm currently try to deal with use the VAE-LSTEM. When I try to run my program it shows me this error:AttributeError: 'bool' object has no attribute 'op' This is gitgub url:...
user avatar
2votes
1answer
36views

How to find size or shape of an tensorflow.python.data.ops.dataset_ops.MapDataset object, output of make_csv_dataset

Using make_csv_dataset we could read an CSV file to tensorflow dataset object csv_data = tf.data.experimental.make_csv_dataset( "./train.csv", batch_size=8190, num_epochs=1, ...
user avatar
  • 603
0votes
1answer
10views

understanding tensorflow Recommending movies: retrieval / usage of : in python class /usage of : in python function

I was reading and trying to work with below documentation from tensorflow https://www.tensorflow.org/recommenders/examples/basic_retrieval?hl=sl In this we have implementation of MovielenseModel class....
user avatar
  • 603
0votes
0answers
7views

tf.train.get_checkpoint_state is always None

I want to store and restore checkpoints, While restoring although it shows checkpoint directory but "tf.train.get_checkpoint_state is None. def save(self, step, model_name='main'): ...
user avatar
0votes
0answers
11views

how to change tensorflow build version?

I am trying to build tensorflow from source following this link. Everything works good and I successfully build it based on master branch. After I get the .whl package, I installed it and checked the ...
user avatar
0votes
0answers
62views

K-fold cross validation with keras tuner hyper parameter search

I am trying to create a model using keras tuner and k-fold cross validation. What I am trying to do by using k-fold cross validation with hyperparameter selection is to find which model has the best ...
user avatar
0votes
0answers
12views

TF-Agent have ValueError: Could not find matching function to call loaded from the SavedModel. Not dtype error

I have trained a DQN agent and have some problems when I'm in action with time_step. But I think the save and load policy is working a good job. # Save Policy my_policy = tf_agent.collect_policy ...
user avatar
0votes
0answers
9views

Tensor flow model import error as NewRandomFileAccess

I get this error when i try to load the model into keras as pb file. This is how file structure looks like -SavedModel -variables variables.index saved_model.pb -SavedImgModel -variables ...
user avatar
  • 11
0votes
0answers
45views

Huggingface error while training model with custom data

I am using the following notebook to train distilbert : https://github.com/krishnaik06/Huggingfacetransformer/blob/main/Custom_Sentiment_Analysis.ipynb I'm using transformers==4.13.0 for the task. ...
user avatar
  • 11
1vote
1answer
27views

Specific options missing in keras layer class

I would like to implement operations on the results of two keras conv2d layers (Ix,Iy) in a deep learning architecture for a computer vision task. The operation looks as follows: G = np.hypot(Ix, Iy) ...
user avatar
0votes
1answer
14views

Conflict of python versions and winerror 5

I installed Python 3.9 and when in cmd I use python3 --version it gives python 3.10.2. It could be the reason for WinError 5 access denied when I try to install tensorflow?
user avatar
0votes
1answer
44views

How to Arrange list of object detection bounding box from right to left and top to bottom?

I'm trying to sort the list of bounding boxes obtained after object detection from right to left and top to down. Below are the bounding box locations bbox = [(637, 207, 681, 207), (679, 99, 726, 99),...
user avatar
0votes
0answers
25views

"SystemError: <built-in function TFE_Py_TapeWatch> returned a result with an error set" whats the problem in tensorflow?

When I do some tensorflow tutorial the error was happened: "SystemError: returned a result with an error set" my code is import tensorflow as tf hei = 170 size = 260 a = tf.Variable(0.1) b ...
user avatar
0votes
1answer
27views

Keras XOR not training

We have been trying for a while to get this to work. This is probably the easiest example to create and so now we need help. We've been changing the number of epochs in the fit function and that's ...
user avatar
0votes
0answers
18views

None Output from MixtureSameFamily Tensorflow

I am trying to learn multi modal distribution using Neural Network and Gaussian Mixture model. but, in my modal summary the output layer has None output, and it is from using MixtureSameFamily. Can ...
user avatar
0votes
1answer
46views

How to use Java to implement code to serialize protobuf object in memory?

I want to know how to use Java to do the same thing like this : exam_input = tf.constant([example_proto.SerializeToString()]) I try to do something like this: val result = sparkEnv.spark.read....
user avatar
  • 331
0votes
0answers
7views

Could not dump a pickled array generated from TimeseriesGenerator by tensorflow

I wanted to transfer my processed data from local machine to google colab, so I pickled my processed data. But when I pickle.load() the pickle file. It contains the TimeseriesGenerator object, instead ...
user avatar
-1votes
0answers
14views

tensorflow.CppShapeInferenceResult.HandleShapeAndType.specialized_type: ".tensorflow.SpecializedType" is not defined

I'm getting this error while importing tensoflow --------------------------------------------------------------------------- TypeError Traceback (most recent call last) ...
user avatar
0votes
0answers
18views

How to develop Echo State Network (ESN) from scarch

class ESN(property of esn): def get_weight(shape of weight): I want to develop a python class of ESN(), and it has a function get_weight, In the training time of an NN, I want to fix some of the ...
user avatar
0votes
0answers
16views

Maintaining different python versions for virtual environments

I have 2 different versions of python. 1 is always used with my anaconda and it is 3.9.7. For the vs code, I tend to change the versions according to need. Currently I have a project which requires me ...
user avatar
0votes
0answers
28views

I got this error - 172:3 : Message type "object_detection.protos.TrainConfig" has no field named "fine_tune_checkpoint_version"

I am using tensorflow for object detection. I ran following command config = config_util.get_configs_from_pipeline_file(files['PIPELINE_CONFIG']) and I got following error ----------------------------...
user avatar
0votes
0answers
50views

ParseError: 21:11 : Message type "object_detection.protos.Initializer" has no field named "random_normal_initializer"

After changing tf.gfile.GFile to tf.io.gfile.GFile in Config_util.py file of Object_detection library, I am getting this error in text_format function can somebody tell how to solve this error. ...
user avatar
0votes
1answer
40views

Why is the length of the word_index greater than num_words?

I have a code, about text preprocessing for deep learning: from keras.preprocessing.text import Tokenizer from keras.preprocessing.sequence import pad_sequences tokenizer = Tokenizer(num_words = ...
user avatar
0votes
0answers
57views

ImportError: cannot import name 'trace'

I'm trying to run AttGAN-tensorflow code https://github.com/LynnHo/AttGAN-Tensorflow but it produces the following error: Traceback (most recent call last): File "train.py", line 7, in <...
user avatar
1vote
0answers
36views

Tensorflow Text Generator

I am trying to train a TF model on a load of text, and unfortunatly if I straight up use model.fit() I run out of RAM very quickly. Could someone help with making it use less RAM (e.g. use a generator ...
user avatar
0votes
0answers
78views

I install tensorflow using pip but tensorflow import does not work

I have installed tensorflow like so: pip3.8 install tensorflow (I am using pip3.8 command as I have several python versions installed on my EC2 instance). When I do so I get this output: Defaulting to ...
user avatar
1vote
1answer
52views

Bidirectional RNN - 'NoneType' object has no attribute '_inbound_nodes' error

I wanna build a Recurrence model which do POS(Part Of Speech tagging) task. It gets input sentence and outputs tags of each words: DT NN VBD DT NN the dog ate the cat I wanna use 'bidirectional ...
user avatar
  • 45
0votes
0answers
17views

tensorflow 2.7 load saved model error with java

I have saved a model in saved model format with tf2.7 and loaded success using: model = tf.saved_model.load(export_dir=export_dir) when i use saved_model_cli to check this model, it rereturns: ...
user avatar
  • 331
0votes
1answer
268views

HuggingFace | ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet con

Not always, but occasionally when running my code this error appears. At first, I doubted it was a connectivity issue but to do with cashing issue, as discussed on an older Git Issue. Clearing cache ...
user avatar
0votes
0answers
24views

Is it possible to renject decoder's output as input for decoder?

I'm trying to build a tensorflow model, using keras, particularly an autoencoder for anomaly detection. My input is a sequence of physical values. I want to use as decoder's input (as usual) the ...
user avatar
0votes
1answer
30views

IndexError: tuple index out of range in tf.Model.fit()

I am trying to train my first network in tensorflow and get the 'IndexError: tuple index out of range'. Here is the source code: model = keras.Sequential() model.add(keras.Input(shape=(104,))) model....
user avatar
  • 1
-1votes
0answers
14views

Values remaining constant for custom Tensorflow Fireworks Optimizer

I have been trying to adapt THIS (click here), implementation of Fireworks Algorithm for optimization into a custom Tensorflow Optimizer. The model is compiling and running but the values remain ...
user avatar
-1votes
0answers
25views

Tensorflow for Mac M1: Import error when trying to import tensorflow

I followed this video to install TensorFlow on my Mac M1. At first, everything worked fine and I could create some simple test models. But a day later I got an import error whenever I try to import ...
user avatar
0votes
0answers
17views

Why not use `from tf import keras`

I have import tensorflow as tf,When I want use tensorflow.kera. Why i should from tensorflow import keras, instead from tf import keras.
user avatar
  • 1
1vote
1answer
21views

Getting encoded output when I print hindi text from a tensorflow dataset

I'm using this corpus for an NLP task. When I read the file and store the hindi and english lines into separate lists, I get string literal outputs like so: def extract_lines(fp): return [line....
user avatar
2votes
1answer
52views

Overwrite plot every epoch

I wrote a little script that has Neural Network approximate polynomial, and plots the result every epoch, but the problem is that I want that every iteration the new plot will overwrite the previous ...
user avatar
  • 127
0votes
0answers
230views

InvalidArgumentError: Graph execution error

I am trying to apply LCM (linear coregionalization model), as a Gaussian process, to a CSV file dataset. This dataset includes two inputs (FracYear, Auxiliar) and two outputs (VV,VH). import gpflow as ...
user avatar
  • 1
0votes
0answers
73views

pip install spacy-universal-sentence-encoder is failed with below error in miniconda3 - Apple M1 MacOS 12.1:

I am trying to perform pip install spacy-universal-sentence-encoder in a miniconda3 docker container with python3.9.5, spacy and tensorflow already installed. I am using MacOS 12.1 with Apple M1 ...
user avatar
  • 11
1vote
0answers
22views

Program modify load vgg16.ckpt file method (original Linux to windows)

I install the Faste-RCNN script from here, this version is modified to fit python3. After following all the instructions I still got an error as below: Loading initial model weights from ./data/...
user avatar
0votes
0answers
25views

Why does my model gives nan and inf loss?

My model is giving inf and NaN in loss and loss_vallidation. My dataset is made by 4 clases. First I've got the following tensor types : BDADDR uint64 CLK uint64 dtype: object Z1 uint64 Z2 ...
user avatar
  • 37
0votes
0answers
43views

ValueError: Shapes (None, 8) and (None, 3) are incompatible

Sorry for my bad english I have this error ValueError: Shapes (None, 8) and (None, 3) are incompatible And this is my model num_of_classes = get_num_of_classes() model = Sequential() ...
user avatar
0votes
1answer
34views

Tensorflow error "No module named 'tensorflow_core.estimator'"

I built a new environment in conda using the following .yml file: name: py37 channels: conda-forge defaults dependencies: python=3.7.7 cartopy=0.18.0 earthengine-api=0.1.221 flake8=3.8.1 jupyterlab=2....
user avatar
  • 117
0votes
0answers
22views

Fitting a BERT model

I have recently started up with NLP BERT sentiment analysis. I used the following code which is originally from a tensorflow blog. def build_classifier_model(): input_text=tf.keras.layers.Input(...
user avatar

15 30 50 per page
1
2 3 4 5
92