Shamane Siri

Converging of the network for different data sets?

6

I tried to train this network to identify 13 classes with 5 RGB images for each class. One image is like this.  I modified the network to work with...

Can you please explain about the accuracy mechanism in the model ?

1

In [this](https://github.com/snowkylin/ntm/blob/master/one_shot_learning.py#L152) line you calculate accuracies for a batch up to first 10 elements in the total list which has 50 indexes. I think you are trying to measure accuracy...

Can You please upload the link to the data set(MANN) ?

1

I assumed you have used [this](https://github.com/brendenlake/omniglot/blob/master/python/images_background.zip) data set. But it has only 964 classes. But you have used a number of training and testing classes respectively 1200 and 423. Also...

[QST] Accessing the model architectures separately.

1

Similar HuggingFace Transformers is there a way to import model architectures and explore them. from transformers import BertModel, BertConfig ``` # Initializing a BERT bert-base-uncased style configuration configuration = BertConfig()...

[QST] How to create a schema from a json file.

2

``` from transformers4rec import torch as tr **schema: tr.Schema = tr.data.tabular_sequence_testing_data.schema # Or read schema from disk: tr.Schema().from_json(SCHEMA_PATH)** ``` I want to understand how to convert a custom dataset compatible...

In the input module how to embed the information that coming from the context? In some papers it has mentioned The will concatenate all the words in the context and...