Skip to main content
656 questions
Newest Active Bountied Unanswered
Filter by
Sorted by
Tagged with
0 votes
0 answers
68 views

I can't use tf.estimator in my code with tensorflow 2.16. Below is the error: AttributeError Traceback (most recent call last) Cell In[17], line 1 ----> 1 linear_est = tf....
Titus Kiptoo's user avatar
  • 1
0 votes
3 answers
6k views

I'm doing an object detection project on the raspi-5 and i run this code on the cmd line python Tensorflow/models/research/object_detection/model_main_tf2.py --model_dir=Tensorflow/workspace/models/...
codrjun's user avatar
  • 1
-1 votes
1 answer
104 views

I am running two tensorflow models using the tf.estimator.train_and_evaluate function one after the other. # The first train_spec = tf.estimator.TrainSpec(input_fn=my_input_fn("train"), ...
Ergun Bicici's user avatar
  • 21
0 votes
1 answer
112 views

I want use DenseHashTable lookup string tensors, just like this answeranswer , keys' type is tf.string, value is embedding with tf.float32 dtype. But when keys is multi-dimensional, error occurs. keys ...
Eugene Deng's user avatar
  • 3
1 vote
1 answer
80 views

Is there any way to show the training progress from the TensorFlow linear estimator: tf.estimator.LinearClassifier().train() similar to how the progress output would be with a model.fit() for each ...
Neutrino404's user avatar
  • 19
0 votes
0 answers
416 views

I installed the GPU-supported tesnorflow 2.2.0, on my machine, then I created a virtual enviorment using conda: conda create --name tfgpu220 python==3.8 And I run these installation commands: pip ...
Ahmed's user avatar
  • 131
1 vote
0 answers
149 views

There are some high level API's in Tensorflow 1 called Estimators. It's a collection of common ML algorithms. However, in the documentation it is stated that Estimators are not recommended for new ...
Jiren's user avatar
  • 681
0 votes
1 answer
188 views

I'm trying to use BigQuery ML to load a saved tensorflow model to make predictions. However when I run the query that read the saved model in GCS I got the following error: TensorFlow SavedModel ...
Marco Abbatangelo's user avatar
  • 87
11 votes
2 answers
7k views

Running estimator from tensorflow today and came up with this error, any idea how to solve it? File "C:\Users\ASUS Laptop\anaconda3\envs\tf_gpu\lib\site-packages\tensorflow_estimator\python\...
簡亞倫's user avatar
  • 121
1 vote
0 answers
174 views

I trainning the same model through keras and estimator with TensorFlow in CPU, and found that keras was much slower than estimator. batch_size = 256 emb_hash_bucket_size = 5000000 emb_dimension = 100 ...
PWZER's user avatar
  • 11
1 vote
1 answer
12k views

I am trying to use linear classifier to predict, the constructing and training of the estimator is listed here: model = tf.estimator.LinearClassifier( n_classes = 2, model_dir = "ongoing"...
RA.IBOY's user avatar
  • 111
1 vote
1 answer
902 views

I am trying to deploying deep learning model on two GPUs with single machine. I am utilizing TensorFlow mirror strategy. I am getting the following error: Traceback (most recent call last): Code ...
Ahmad's user avatar
  • 774
0 votes
1 answer
2k views

excuse my english. I've been trying to handle Estimators API of tensorflow (v2.x), but when i'm trying to convert a model from tf.estimators to tflite with this code : import tensorflow as tf import ...
kaii723's user avatar
  • 1
33 votes
8 answers
54k views

When using tensorflow, I have the following error messages ERROR:root:Internal Python error in the inspect module. Below is the traceback from this internal error.' File "<frozen importlib....
user297850's user avatar
  • 8,065
1 vote
0 answers
195 views

I am trying to use a custom Estimator together with a feed_dict. Based on several relevant questions, such as this one, I have arrived at the following code. Note that I am returning dataset from ...
jdmux's user avatar
  • 11
1 vote
1 answer
184 views

I'm facing some issues regarding the behavior of the training loop of Tensorflow's Estimator and Dataset APIs. The code is as follows (tf2.3): NUM_EXAMPLES = X_train.shape[0] # dataset has 8000 ...
Ali's user avatar
  • 4,536
0 votes
0 answers
102 views

Problem Description I'm using tensorflow Estimator API, and have encountered a weird phenomenon. I'm passing the exact same input_fn to both training and evaluation, and for some reason the images ...
yonatansc97's user avatar
  • 699
1 vote
1 answer
852 views

I am trying to implement early stopping in TF OD API. I used this code. Here is my EarlyStoppingHook (is it essentially just a copy from the above code): class EarlyStoppingHook(session_run_hook....
Danil Kononyhin's user avatar
  • 316
0 votes
1 answer
427 views

How can I create two sets of shared embeddings from the same tensorflow feature columns? This small example import tensorflow as tf data = {"A": [0, 1, 2, 3], "B": [2, 1, 0, 3]} ...
MrCartoonology's user avatar
  • 2,097
1 vote
0 answers
142 views

I'm trying to upgrade my model to use AI-Platform 2.1 instead of 1.15, but I can't get the FinalExporter to work. I followed the steps outlined in ai-platform: No eval folder or export folder in ...
sven's user avatar
  • 11
2 votes
0 answers
357 views

I'm aware that they are already provided in model.config by using something like: data_augmentation_options { random_adjust_contrast { } } However, I need to perform my own data ...
RayCo5514's user avatar
  • 21
0 votes
1 answer
136 views

I want to sample datas using weighted distribution (probability) The examples are like below: class distribution: doc_distribution = {0: 40, 1: 18, 2: 8, 3: 598, ... , 9: 177} I would to make the ...
Gi Yeon Shin's user avatar
  • 367
0 votes
1 answer
330 views

I have created an Estimator from a TF Slim Resnet V2 checkpoint and tested it to make predictions. The main thing of what I did is basically similar to a normal Estimator together with ...
Minh Nguyen's user avatar
  • 875
1 vote
1 answer
297 views

I've implemented the following model using the DNNClassifier class. The model is parametrized as follows classifier = tf.estimator.DNNClassifier( hidden_units=[60, 30, 20], ...
ezy's user avatar
  • 59
1 vote
2 answers
459 views

I want to construct a batch of data with batchsize 16, using tf.data, where [:8] is a kind of data A, [8:16] is a kind of data B. It is easy to do without tf.data. If use tf.data, the code could be: ...
CoderOnly's user avatar
  • 1,740
0 votes
1 answer
563 views

I am trying to build an TensorFlow2 estimator from a custom Keras model. The model takes as input a tensor of shape [batch_size, n, h, w, c]. I need to apply a CNN on each [n, h, w, c] tensor from the ...
beardybear's user avatar
  • 159
0 votes
1 answer
256 views

I'm trying to follow this guide to load a SavedModel. I first save the trained model as follows feature_columns >>> [NumericColumn(key='Fwd_IAT_Total', shape=(1,), default_value=None, dtype=...
ezy's user avatar
  • 59
2 votes
1 answer
78 views

I am pretraining BERT in 1 machine with 4 GPU, not 1 GPU. For each training step, I am wondering whether the input_fn give 1 GPU 1 batch or give 4 GPU 1 batch. The mirrow strategy code: ...
CoderOnly's user avatar
  • 1,740
0 votes
1 answer
710 views

Very beginner question, I hope that's fine I'm trying to train this model from GitHub with the MAPS dataset and I made new .tfrecords with this code for the train set. It is based from the code here ...
intrusiveVoyager's user avatar
  • 33
2 votes
1 answer
162 views

I just converted an existing project from TF 1.14 to TF 2.1 which uses the TPUEstimator API. After making the conversion, testing locally (i.e. use_tpu=False) runs successfully. However, I am getting ...
Nicholas Breckwoldt's user avatar
  • 41
6 votes
1 answer
1k views

I'm trying to train a DNNClassifier labels = ['BENIGN', 'Syn', 'UDPLag', 'UDP', 'LDAP', 'MSSQL', 'NetBIOS', 'WebDDoS'] # Build a DNN classifier = tf.estimator.DNNClassifier( ...
ezy's user avatar
  • 59
1 vote
1 answer
275 views

I am pretraining BERT in 1 machine with 4 GPU. The input function code: def input_fn(params): """The actual input function.""" batch_size = FLAGS.train_batch_size ...
CoderOnly's user avatar
  • 1,740
0 votes
1 answer
256 views

I trained a classifier for my own dataset using TF Estimators, but after each prediction call I'll get different prediction results. I checked the dataset and the data example order is alright , same ...
zr f's user avatar
  • 1
1 vote
0 answers
220 views

I tried to use numpy inside cnn_model.evaluate(), but it gave AttributeError: 'Tensor' object has no attribute 'numpy'. I used numpy to calculate accuracy and mean squared error using tf.keras.metrics....
beginnercoder's user avatar
  • 91
0 votes
1 answer
178 views

I can't seem to find the issue in the code that causes the error. I would appreciate it if you could help. Thanks in advance! The error generated from the code below is TypeError: '...
LLTeng's user avatar
  • 395
0 votes
1 answer
193 views

I'm running a training job on gcp ai-platform for tensorflow estimators with mirrored distribution strategy with --python-version 3.7 and --runtime-version 2.1. I'm providing the necessary code ...
Swapnil Masurekar's user avatar
  • 498
1 vote
0 answers
58 views

I'm new in using TF. For some reasons, I have to use TF1.10, where I found that .ppm is not supported by tf.image.decode_image. The final goal of my network is, to read a RGBD input, and use it to ...
sssssy's user avatar
  • 13
0 votes
1 answer
255 views

I am trying to understand a model built with the tensorflow Estimator framework. I'd like to use the Hooks API to add ops that process the input during evaluation, or prediction. It seems I should ...
MrCartoonology's user avatar
  • 2,097
0 votes
1 answer
212 views

I am Experimenting with Text Classification for character_rnn (https://github.com/tensorflow/tensorflow/blob/671baf080238025da9698ea980cd9504005f727c/tensorflow/examples/learn/...
SWAYAM MITTAL's user avatar
  • 11
1 vote
0 answers
480 views

After exporting my saved_model.pb file, I would like to convert it in TfLite. I had the same error than this post. So I tried the proposed answer : import tensorflow as tf export_dir = './saved/...
Joachimhgg's user avatar
  • 57
1 vote
0 answers
258 views

TensorFlow Estimators (tf.estimator) are "high level tools for working with models". Instead of defining your own DNN classifier layer by layer there is already an estimator for that. ...
Domedagen's user avatar
  • 11
3 votes
1 answer
565 views

I'm stuck on one line of code and have been stalled on a project all weekend as a result. I am working on a project that uses BERT for sentence classification. I have successfully trained the model, ...
David Stein's user avatar
  • 865
0 votes
1 answer
275 views

remote: [20:44:36+0000] Collecting tensorflow==2.1.0 remote: [20:44:36+0000] Downloading tensorflow-2.1.0-cp37-cp37m-manylinux2010_x86_64.whl (421.8 MB) remote: .......................................
Abhishek Kargawal's user avatar
  • 401
0 votes
1 answer
503 views

First of all, I am using TFX version 0.21.2 and Tensorflow version 2.1. I have constructed a pipeline largely following the Chigaco taxi example. When the Trainer component is executed I can see the ...
Panagiotis Kourouklidis's user avatar
  • 51
1 vote
1 answer
149 views

I have trained a Linear regression model using tensorflow. I have both numerical and categorical features. For this example, one of the categorical features is "has_Alt", which takes a value of either ...
dhamechaSpeaks's user avatar
  • 157
0 votes
0 answers
81 views

I am new dealing with the tf.estimators api. I have a Dnn classifier that is giving me an accuracy of 60% on the JM1 Software defect prediction dataset from PROMISE repository. I want to imporve the ...
SAI PRATYUSHA's user avatar
  • 88
0 votes
1 answer
200 views

I am working on DNNClassifier from Tensor flow estimation and used data set is JM1 (Defect Prediction ) Considered training features 0:8163(defects-free:6056, defects: 2106) Considered validating ...
Suresh Reshu's user avatar
  • 9
0 votes
1 answer
103 views

I have a saved DNN estimator model. How can I restore the model for prediction? I saved my model using: #Create the input function input_func = tf.estimator.inputs.pandas_input_fn(x=X_train, y=...
Léo SOHEILY KHAH's user avatar
  • 787
1 vote
1 answer
682 views

I have a lot of txt files, so I made a dataset following this tutorial of tensorflow: https://www.tensorflow.org/tutorials/load_data/text?hl=es#build_vocabulary My program works with smalls ...
Darome's user avatar
  • 87
4 votes
1 answer
699 views

I am using the Tensorflow estimator and explicitly the method tf.estimator.train_and_evaluate(). There is an early stopping hook for the training which is tf.contrib.estimator....
Marcel's user avatar
  • 41

1
2 3 4 5
…
14