}]
```
Is this what I move to here?
```auto
import datasets
import glob
IMAGES = glob.glob("D:\cropped_image_1080x1080\img_0")
SEG_MAPS = glob.glob("D:.\img_0.jpg")
dataset = datasets.Dataset.from_dict({
"image": IMAGES,
"label": SEG_MAPS
},
features=datasets.Features({
"image":datasets.Image(),
"label":datasets.Image()
})
)
```
I still don’t get how I move the fifth member of this `pipeline` that I got from here
```auto
from transformers import pipeline
semantic_segmentation = pipeline("image-segmentation", "shi-labs/oneformer_ade20k_swin_large")
```
to id2label, do I need to label it as implied in [here](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-set-useful-id2label-and-label2id-in-config-json-using-trainer%2F43545%2F2)%3F
---
**Author:**  [@seand0101](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fseand0101)%5C
**Post date:** [December 15, 2024, 7:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F7 "2024-12-15T07:51:11Z")
How do this work for 8725 images that might have different scores, I still don’t understand the concept behind id2label and pretrained model…
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 15, 2024, 7:54am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F8 "2024-12-15T07:54:27Z")
Oh, it seems to have worked out well. No matter which model you use, it’s better to refer to the author’s model card rather than the automatically generated upper part of the HF.
For this model, it would look something like the link below.
The format required will vary depending on the model, but as long as you make the dataset in a way that is easy for you to use, that should be fine.
Uploading and downloading to HF’s dataset repo and organizing large amounts of data is the forte of the datasets library.
However, there may be a recommended dataset format for HF Trainer.
In the end, it’s the same thing that we need to write a few lines of Python before passing it to the model.😅 I don’t think you need labels for use cases that don’t require labels. I don’t think you need labels for segmentation.
> **[shi-labs/oneformer\_ade20k\_swin\_large · Hugging Face](https://huggingface.co/shi-labs/oneformer_ade20k_swin_large#how-to-use)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
---
**Author:**  [@seand0101](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fseand0101)%5C
**Post date:** [December 15, 2024, 7:56am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F9 "2024-12-15T07:56:07Z")
Then do I only need the mask for training? Every guide I found use id2label though, I understand that this is semantic segmentation so not only it is segmented but its also labelled as something
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 15, 2024, 7:57am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F10 "2024-12-15T07:57:12Z")
Pipelines are convenient, but they perform complex processing internally, so they are like black boxes.
It might be better to try doing it manually at first. The method on the model explanation page is the most general-purpose method.
> Then do I only need the mask for training?
Yes.
> semantic segmentation so not only it is segmented but its also labelled as something
If that’s the case, you may need to label the data set…
It’s difficult to create data that doesn’t exist. Only a large AI or a human being could do it.
---
**Author:**  [@seand0101](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fseand0101)%5C
**Post date:** [December 15, 2024, 8:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F11 "2024-12-15T08:01:37Z")
so I need to id2label for my mask, what should I do with each weight? Sorry I’m still confused and don’t know how to explain it tbh…
I know I need these weights for some fine tuning but I don’t know where to store it as. Or if I train my mask I got from applying the model to my picture is it what I need?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 15, 2024, 8:06am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F12 "2024-12-15T08:06:20Z")
Even if you have to create your own data in the end, semantic segmentation itself is an existing task.
I think there are already working datasets for semantic segmentation that you can use as samples. If you can imitate that structure, it will be the quickest.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [December 15, 2024, 8:09am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F13 "2024-12-15T08:09:26Z")
It seems like you need a mask that uses multiple colors or shades to semantic segmentation. Your mask is black and white, 0 or 1, so it should be usable for two types of classification. I think it should be usable for whether or not it’s a river.
> **[Google Colab](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/semantic_segmentation.ipynb)**
> **[huggingface/semantic-segmentation-test-sample · Datasets at Hugging Face](https://huggingface.co/datasets/huggingface/semantic-segmentation-test-sample)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
> **[moritzef/mapillary\_vistas\_semantic\_edges\_and\_segmentation · Datasets at...](https://huggingface.co/datasets/moritzef/mapillary_vistas_semantic_edges_and_segmentation)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.
by json file like this (or opposite?):
```json
{"0": "not river", "1": "river"}
```
With HF, JSON files that have been carelessly left lying around are sometimes configuration files with fixed file names…😅
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [December 15, 2024, 8:09pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-separate-predictions-map-to-create-id2label-json%2F131146%2F14 "2024-12-15T20:09:29Z")
Closed on December 15, 2024, 8:09pm UTC
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.