# \#epoc **URL:** https://discuss.ai.google.dev/tag/epoc/205.md [Latest](https://discuss.ai.google.dev/latest.md) · [Categories](https://discuss.ai.google.dev/categories.md) · [Tags](https://discuss.ai.google.dev/tags.md) --- ## [Unknown error: Graph execution error](https://discuss.ai.google.dev/t/unknown-error-graph-execution-error/32215)
**Author:** [@Gayathri](https://discuss.ai.google.dev/u/Gayathri)\ **Replies:** 1\ **Last updated:** [March 26, 2026, 12:43pm UTC](https://discuss.ai.google.dev/t/unknown-error-graph-execution-error/32215 "2026-03-26T12:43:08Z")
I’m running into this error while training the model. Couldn’t find any resources online on how to solve it. Link to the complete code - Colab link this is the error message - Epoch 1/100 1/1 \[======================… --- ## [When function call() is called in the custom training?](https://discuss.ai.google.dev/t/when-function-call-is-called-in-the-custom-training/89314)
**Author:** [@DEV\_AI](https://discuss.ai.google.dev/u/DEV_AI)\ **Replies:** 1\ **Last updated:** [July 2, 2025, 3:29pm UTC](https://discuss.ai.google.dev/t/when-function-call-is-called-in-the-custom-training/89314 "2025-07-02T15:29:38Z")
I follow this guide for KD Knowledge Distillation and the source as class Distiller(keras.Model): def \_\_init\_\_(self, student, teacher): super().\_\_init\_\_() self.teacher = teacher self.student … --- ## [Tensorflow records get corrupted randomly (TF 2.15)](https://discuss.ai.google.dev/t/tensorflow-records-get-corrupted-randomly-tf-2-15/71507)
**Author:** [@Cola\_Lightyear](https://discuss.ai.google.dev/u/Cola_Lightyear)\ **Replies:** 1\ **Last updated:** [March 12, 2025, 4:50pm UTC](https://discuss.ai.google.dev/t/tensorflow-records-get-corrupted-randomly-tf-2-15/71507 "2025-03-12T16:50:23Z")
Hi, I am performing a considerable amount of random search iterations to find good hyperparameters of a model. The data I am using is stored in tensorflow records. My model trains fine for many epochs. There have been p… --- ## [Single-sample evaluation (prediction/inference) speed for simple MLP slower in Keras compared to skl](https://discuss.ai.google.dev/t/single-sample-evaluation-prediction-inference-speed-for-simple-mlp-slower-in-keras-compared-to-skl/44107)
**Author:** [@willb](https://discuss.ai.google.dev/u/willb)\ **Replies:** 6\ **Last updated:** [October 30, 2024, 11:47am UTC](https://discuss.ai.google.dev/t/single-sample-evaluation-prediction-inference-speed-for-simple-mlp-slower-in-keras-compared-to-skl/44107 "2024-10-30T11:47:11Z")
Hello, Can someone help me speed understand why a simple keras MLP binary classifier evaluates (predicts) significantly slower for single samples than the skl MLPClassifier, despite it training much quicker than it. I a… --- ## [Low Accuracy and Stagnant Validation Accuracy in BERT Model for Multilabel Classification](https://discuss.ai.google.dev/t/low-accuracy-and-stagnant-validation-accuracy-in-bert-model-for-multilabel-classification/42148)
**Author:** [@Xuan5251](https://discuss.ai.google.dev/u/Xuan5251)\ **Replies:** 4\ **Last updated:** [October 8, 2024, 6:14am UTC](https://discuss.ai.google.dev/t/low-accuracy-and-stagnant-validation-accuracy-in-bert-model-for-multilabel-classification/42148 "2024-10-08T06:14:04Z")
Hello everyone, I’m fine-tuning a BERT-based model for a multilabel classification task. Specifically, I’m trying to predict the Big Five personality traits based on text inputs. However, I’m encountering an issue where… --- ## [CNN Training performance improvements](https://discuss.ai.google.dev/t/cnn-training-performance-improvements/39851)
**Author:** [@Timus](https://discuss.ai.google.dev/u/Timus)\ **Replies:** 3\ **Last updated:** [September 24, 2024, 10:46am UTC](https://discuss.ai.google.dev/t/cnn-training-performance-improvements/39851 "2024-09-24T10:46:25Z")
I have a CNN which I want to classify sleepstages with. I divided the data into epochs of 30 seconds (1.9mio in total) and added all epochs to a tensorflow record (because as far as i researched that should be a pretty f… --- ## [Having problems with training model](https://discuss.ai.google.dev/t/having-problems-with-training-model/38046)
**Author:** [@Bashaar\_Dhoot](https://discuss.ai.google.dev/u/Bashaar_Dhoot)\ **Replies:** 2\ **Last updated:** [September 7, 2024, 7:35pm UTC](https://discuss.ai.google.dev/t/having-problems-with-training-model/38046 "2024-09-07T19:35:58Z")
I am having problems with loading my data to train. I think I have not converted the data types correctly. I am following a tutorial and using copilot and I might have got too confused. here this the error message: Epo… --- ## [How to use tf.distribute.Strategy to distribute training?](https://discuss.ai.google.dev/t/how-to-use-tf-distribute-strategy-to-distribute-training/36004)
**Author:** [@Tosha\_Tang](https://discuss.ai.google.dev/u/Tosha_Tang)\ **Replies:** 2\ **Last updated:** [August 19, 2024, 8:39am UTC](https://discuss.ai.google.dev/t/how-to-use-tf-distribute-strategy-to-distribute-training/36004 "2024-08-19T08:39:48Z")
I want to use tf.distribute.Strategy to distribute the training of my model. But there are some problems in my code below. Can anyone help me? I totally have no ideal about how to fix them and chatgpt didn’t help. impo… --- ## [Why does fit() recalculate num\_batches no matter what I specify for steps\_per\_epoch?](https://discuss.ai.google.dev/t/why-does-fit-recalculate-num-batches-no-matter-what-i-specify-for-steps-per-epoch/20740)
**Author:** [@BreckEmert](https://discuss.ai.google.dev/u/BreckEmert)\ **Replies:** 1\ **Last updated:** [June 14, 2024, 8:56am UTC](https://discuss.ai.google.dev/t/why-does-fit-recalculate-num-batches-no-matter-what-i-specify-for-steps-per-epoch/20740 "2024-06-14T08:56:48Z")
I’m having issues where TF can’t calculate the cardinality of my custom dataset in graph execution mode (its dimension is set to None). But specifying None, 1, or a random int like 5 doesn’t change that it’s always tryi… --- ## [Hey I get accuracy 97 on 50 epoches then after calculation applied I GET 73 LOWEST ACCUARY](https://discuss.ai.google.dev/t/hey-i-get-accuracy-97-on-50-epoches-then-after-calculation-applied-i-get-73-lowest-accuary/30467)
**Author:** [@Palak\_Talreja](https://discuss.ai.google.dev/u/Palak_Talreja)\ **Replies:** 1\ **Last updated:** [May 3, 2024, 8:20am UTC](https://discuss.ai.google.dev/t/hey-i-get-accuracy-97-on-50-epoches-then-after-calculation-applied-i-get-73-lowest-accuary/30467 "2024-05-03T08:20:32Z")
\*\*VIEW THE CODE AND RESOLVE THE ISSUE \*\* https://drive.google.com/file/d/1PDNihjdqw-N3Ud-3Reo4Q6oYL2cHcSOY/view?usp=sharing --- ## [Changing activation function during training](https://discuss.ai.google.dev/t/changing-activation-function-during-training/27795)
**Author:** [@Sebastian\_P](https://discuss.ai.google.dev/u/Sebastian_P)\ **Replies:** 6\ **Last updated:** [April 12, 2024, 11:13am UTC](https://discuss.ai.google.dev/t/changing-activation-function-during-training/27795 "2024-04-12T11:13:32Z")
Hi, I’m currently trying to figure out a way to change my activation function(s) during training. For example consider a leaky relu max(x, x/a) with a = 1 at the start of the training and as the training progresses i wa… --- ## [Weird automatic stopping behavior in TF 2.11 GPU](https://discuss.ai.google.dev/t/weird-automatic-stopping-behavior-in-tf-2-11-gpu/29782)
**Author:** [@shankar\_B](https://discuss.ai.google.dev/u/shankar_B)\ **Replies:** 1\ **Last updated:** [March 22, 2024, 3:04pm UTC](https://discuss.ai.google.dev/t/weird-automatic-stopping-behavior-in-tf-2-11-gpu/29782 "2024-03-22T15:04:50Z")
While training a model using TF 2.11, the training gets stopped periodically without any stack trace. Only the statement ‘Killed’ gets written to the console. For Tesla T4 GPU having 16 GB GPU memory, the training stops … --- ## [Training start up when calling fit() extremly slow for model](https://discuss.ai.google.dev/t/training-start-up-when-calling-fit-extremly-slow-for-model/28327)
**Author:** [@Cola\_Lightyear](https://discuss.ai.google.dev/u/Cola_Lightyear)\ **Replies:** 8\ **Last updated:** [March 1, 2024, 12:39pm UTC](https://discuss.ai.google.dev/t/training-start-up-when-calling-fit-extremly-slow-for-model/28327 "2024-03-01T12:39:43Z")
Hi, a follow up to my other threads: I am benchmarking my new implementation in comparison to my old implementation of my recurrent autoencoder. However, for my new implementation, for some reason the initial startup b… --- ## [My loss function return nan in every epoches since the first to the last](https://discuss.ai.google.dev/t/my-loss-function-return-nan-in-every-epoches-since-the-first-to-the-last/31756)
**Author:** [@micache](https://discuss.ai.google.dev/u/micache)\ **Replies:** 1\ **Last updated:** [February 23, 2024, 4:52pm UTC](https://discuss.ai.google.dev/t/my-loss-function-return-nan-in-every-epoches-since-the-first-to-the-last/31756 "2024-02-23T16:52:54Z")
Hi. Im trying to create a regression model for this dataset on this contest: House Prices - Advanced Regression Techniques | Kaggle I preprocess the dataset with normalization before fit it into the model. I also create… --- ## [Trouble using tfds load to vectorize text](https://discuss.ai.google.dev/t/trouble-using-tfds-load-to-vectorize-text/29081)
**Author:** [@srivassid](https://discuss.ai.google.dev/u/srivassid)\ **Replies:** 2\ **Last updated:** [February 6, 2024, 9:53am UTC](https://discuss.ai.google.dev/t/trouble-using-tfds-load-to-vectorize-text/29081 "2024-02-06T09:53:08Z")
Hello I am trying to vectorize text (wikipedia) using tfds load. I am trying to do something like this This nlp example contains imdb reviews data and i was able to successfully follow it. But i am not able to do it fo… --- ## [Network Appears To Stop Learning Early](https://discuss.ai.google.dev/t/network-appears-to-stop-learning-early/31418)
**Author:** [@ImMe](https://discuss.ai.google.dev/u/ImMe)\ **Replies:** 2\ **Last updated:** [January 27, 2024, 6:37pm UTC](https://discuss.ai.google.dev/t/network-appears-to-stop-learning-early/31418 "2024-01-27T18:37:31Z")
Hi, I recently became interested in machine learning, more specifically, neural networks. I have gone over a bit of introductory material on the topic and I am attempting to test my understanding of it so far. The task … --- ## [How to speedup input pipeline beyond vectorize and num\_parallel\_calls?](https://discuss.ai.google.dev/t/how-to-speedup-input-pipeline-beyond-vectorize-and-num-parallel-calls/29715)
**Author:** [@gwiesenekker](https://discuss.ai.google.dev/u/gwiesenekker)\ **Replies:** 2\ **Last updated:** [January 17, 2024, 6:46pm UTC](https://discuss.ai.google.dev/t/how-to-speedup-input-pipeline-beyond-vectorize-and-num-parallel-calls/29715 "2024-01-17T18:46:38Z")
Hi, I have 300M 192 one-hot inputs encoded as 24 8-byte ints residing in memory. I have defined a function to unpack them: def unpackbits\_tf(features, labels): mask = tf.constant(\[128, 64, 32, 16, 8, 4, 2, 1\], dtype=… --- ## [Graph execution error which I can't find anything about](https://discuss.ai.google.dev/t/graph-execution-error-which-i-cant-find-anything-about/28780)
**Author:** [@pasator\_man](https://discuss.ai.google.dev/u/pasator_man)\ **Replies:** 1\ **Last updated:** [January 8, 2024, 6:55am UTC](https://discuss.ai.google.dev/t/graph-execution-error-which-i-cant-find-anything-about/28780 "2024-01-08T06:55:07Z")
I am encountering this error which I can’t find anything about. I don’t have a variable called max\_seq\_length and I haven’t been able to find what it’s for. InvalidArgumentError Traceback (most rece… --- ## [Input ran out of data interrupting training](https://discuss.ai.google.dev/t/input-ran-out-of-data-interrupting-training/31714)
**Author:** [@matca](https://discuss.ai.google.dev/u/matca)\ **Replies:** 1\ **Last updated:** [January 5, 2024, 8:48am UTC](https://discuss.ai.google.dev/t/input-ran-out-of-data-interrupting-training/31714 "2024-01-05T08:48:25Z")
I am working in a tumor segmentation, the images are 3D in nifti format (MRI Images). I created a data generator because if I uploaded the full dataset to RAM, it crashes due to the 3D images. The dataset is composed by … --- ## [tf.keras.Sequential().compile error](https://discuss.ai.google.dev/t/tf-keras-sequential-compile-error/28614)
**Author:** [@Yogesh](https://discuss.ai.google.dev/u/Yogesh)\ **Replies:** 3\ **Last updated:** [January 1, 2024, 5:13am UTC](https://discuss.ai.google.dev/t/tf-keras-sequential-compile-error/28614 "2024-01-01T05:13:37Z")
Hello guys, I was trying to run classification model on fashion mnist dataset, following book " Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition" . Section 10. Introduction to Artificial N… --- ## [Managing dataset with unbalanced labels](https://discuss.ai.google.dev/t/managing-dataset-with-unbalanced-labels/30188)
**Author:** [@sollted\_sollted](https://discuss.ai.google.dev/u/sollted_sollted)\ **Replies:** 4\ **Last updated:** [December 26, 2023, 11:50am UTC](https://discuss.ai.google.dev/t/managing-dataset-with-unbalanced-labels/30188 "2023-12-26T11:50:33Z")
i am training on dataset which has three classes :class, sum of labels: 0, 3132 1, 492 -1, 12 as you can see there is huge inbalance here so wanted to fix it using class weights (maybe there is better way). So i crea… --- ## [Code is stuck at epoch 1 in lazy mode](https://discuss.ai.google.dev/t/code-is-stuck-at-epoch-1-in-lazy-mode/26800)
**Author:** [@blessedg](https://discuss.ai.google.dev/u/blessedg)\ **Replies:** 5\ **Last updated:** [December 26, 2023, 5:51am UTC](https://discuss.ai.google.dev/t/code-is-stuck-at-epoch-1-in-lazy-mode/26800 "2023-12-26T05:51:48Z")
my code below is stuck at epoch 1 and wont run in lazy mode due to the loop “for i, routers\_indice in enumerate(routers\_indices)” without that loop it runs fine. its taking too long to run in eager mode class Baselin…