# Memory Error

**URL:** <https://forum.rasa.com/t/memory-error/20889>\
**Category:** Rasa Open Source\
**Created:** [November 5, 2019, 5:52am UTC](https://forum.rasa.com/t/memory-error/20889 "2019-11-05T05:52:12Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Akanksha1](https://avatars.discourse-cdn.com/v4/letter/a/b3f665/32.png) [@Akanksha1](https://forum.rasa.com/u/Akanksha1)\
**Post date:** [November 5, 2019, 5:52am UTC](https://forum.rasa.com/t/memory-error/20889/1 "2019-11-05T05:52:12Z")

</div>

**MemoryError: Unable to allocate array with shape (1000, 1369, 1369) and data type float32** during train large nlu data.

Nlu data size = 5.5mb

Machine size =

```
                 total used free shared buff/cache available
           Mem: 31G 10G 19G 16M 1.3G 20G
           Swap: 0B 0B 0B

        when I start training Nlu data Memory size decreases as
          total - 31G used - 10G free - 19G shared - 16M buff/cache - 1.3G available - 20G
                    
          total - 31G used - 19G free - 10G shared - 16M buff/cache - 1.3G available - 20G

          total - 31G used - 26G free - 3.4G shared - 16M buff/cache - 1.3G available - 20G

          total - 31G used - 28G free - 840M shared - 16M buff/cache - 1.3G available - 20G

```

can you tell me why memory decreases in this ratio.

NLU version = 0.13.7

Pipeline used -

- name: tokenizer\_whitespace
- name: intent\_entity\_featurizer\_regex
- name: ner\_crf
- name: intent\_featurizer\_count\_vectors analyzer: ‘word’ min\_ngram: 1 # int max\_ngram: 2 # int
- name: intent\_classifier\_tensorflow\_embedding epochs: 100 language: en

According to this [https://medium.com/rasa-blog/supervised-word-vectors-from-scratch-in-rasa-nlu-6daf794efcd8\*](https://medium.com/rasa-blog/supervised-word-vectors-from-scratch-in-rasa-nlu-6daf794efcd8*) 6000 labeled utterances took up just 120 Mb.

---

<div class="post-metadata">

**Author:** ![dakshvar22](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/dakshvar22/32/3993_2.png) [@dakshvar22](https://forum.rasa.com/u/dakshvar22)\
**Post date:** [November 5, 2019, 1:06pm UTC](https://forum.rasa.com/t/memory-error/20889/2 "2019-11-05T13:06:06Z")

</div>

@Akanksha1 Can you please update to latest Rasa version and see if the problem still persists?

---

<div class="post-metadata">

**Author:** ![Akanksha1](https://avatars.discourse-cdn.com/v4/letter/a/b3f665/32.png) [@Akanksha1](https://forum.rasa.com/u/Akanksha1)\
**Post date:** [November 7, 2019, 9:34am UTC](https://forum.rasa.com/t/memory-error/20889/3 "2019-11-07T09:34:59Z")

</div>

@dakshvar22 Train on new version of rasa (rasa version - 1.3.6) But no improvement in training.

---

<div class="post-metadata">

**Author:** ![dakshvar22](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/dakshvar22/32/3993_2.png) [@dakshvar22](https://forum.rasa.com/u/dakshvar22)\
**Post date:** [November 8, 2019, 11:38am UTC](https://forum.rasa.com/t/memory-error/20889/4 "2019-11-08T11:38:32Z")

</div>

@Akanksha1 In your configuration for `EmbeddingIntentClassifier` , can you add `batch_strategy: sequence` and report if the result stays the same?