adam-bourne
commited on
Commit
•
2a89537
1
Parent(s):
35e51b0
Update model card with more detailed info after pushing to hub
Browse files
README.md
CHANGED
@@ -5,14 +5,16 @@ tags:
|
|
5 |
model-index:
|
6 |
- name: food-classifier
|
7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
-
probably proofread and complete it, then remove this comment. -->
|
12 |
-
|
13 |
# food-classifier
|
14 |
|
15 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
16 |
It achieves the following results on the evaluation set:
|
17 |
- Train Loss: 0.2136
|
18 |
- Validation Loss: 0.2284
|
@@ -21,17 +23,15 @@ It achieves the following results on the evaluation set:
|
|
21 |
|
22 |
## Model description
|
23 |
|
24 |
-
|
25 |
|
26 |
## Intended uses & limitations
|
27 |
|
28 |
-
|
29 |
|
30 |
## Training and evaluation data
|
31 |
|
32 |
-
|
33 |
-
|
34 |
-
## Training procedure
|
35 |
|
36 |
### Training hyperparameters
|
37 |
|
@@ -55,4 +55,4 @@ The following hyperparameters were used during training:
|
|
55 |
- Transformers 4.30.2
|
56 |
- TensorFlow 2.12.0
|
57 |
- Datasets 2.13.1
|
58 |
-
- Tokenizers 0.13.3
|
|
|
5 |
model-index:
|
6 |
- name: food-classifier
|
7 |
results: []
|
8 |
+
datasets:
|
9 |
+
- food101
|
10 |
+
metrics:
|
11 |
+
- accuracy
|
12 |
+
library_name: transformers
|
13 |
---
|
14 |
|
|
|
|
|
|
|
15 |
# food-classifier
|
16 |
|
17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
- Train Loss: 0.2136
|
20 |
- Validation Loss: 0.2284
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
26 |
+
This is an image classification model fine tuned from the Google Vision Transformer (ViT) to classify images of food.
|
27 |
|
28 |
## Intended uses & limitations
|
29 |
|
30 |
+
For messing around!
|
31 |
|
32 |
## Training and evaluation data
|
33 |
|
34 |
+
The training set contained 101 food classes, over a dataset of 101,000 images. The train/eval split was 80/20
|
|
|
|
|
35 |
|
36 |
### Training hyperparameters
|
37 |
|
|
|
55 |
- Transformers 4.30.2
|
56 |
- TensorFlow 2.12.0
|
57 |
- Datasets 2.13.1
|
58 |
+
- Tokenizers 0.13.3
|