RealFalconsAI commited on
Commit
85fb89f
1 Parent(s): 121fba2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -8,7 +8,8 @@ pipeline_tag: image-classification
8
 
9
  The **Fine-Tuned Vision Transformer (ViT)** is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for image classification tasks. This specific model, named "google/vit-base-patch16-224-in21k," is pre-trained on a substantial collection of images in a supervised manner, leveraging the ImageNet-21k dataset. The images in the pre-training dataset are resized to a resolution of 224x224 pixels, making it suitable for a wide range of image recognition tasks.
10
 
11
- During the pre-training phase, the model underwent training for fewer than 20 epochs with a batch size of 16. This training process involved learning valuable visual features from the ImageNet-21k dataset to create a robust foundation for subsequent fine-tuning on specific tasks.
 
12
 
13
  ## Intended Uses & Limitations
14
 
@@ -53,7 +54,8 @@ model.config.id2label[predicted_label]
53
  <hr>
54
 
55
  ### Limitations
56
- - **Specialized Task Fine-Tuning**: While the model is adept at NSFW image classification, its performance may vary when applied to other tasks. Users interested in employing this model for different tasks should explore fine-tuned versions available in the model hub for optimal results.
 
57
 
58
  ## Training Data
59
 
 
8
 
9
  The **Fine-Tuned Vision Transformer (ViT)** is a variant of the transformer encoder architecture, similar to BERT, that has been adapted for image classification tasks. This specific model, named "google/vit-base-patch16-224-in21k," is pre-trained on a substantial collection of images in a supervised manner, leveraging the ImageNet-21k dataset. The images in the pre-training dataset are resized to a resolution of 224x224 pixels, making it suitable for a wide range of image recognition tasks.
10
 
11
+ During the pre-training phase, the model underwent training for fewer than 20 epochs with a batch size of 16.
12
+ This training process involved learning valuable visual features from the dataset to create a robust foundation for this specific tasks.
13
 
14
  ## Intended Uses & Limitations
15
 
 
54
  <hr>
55
 
56
  ### Limitations
57
+ - **Specialized Task Fine-Tuning**: While the model is adept at NSFW image classification, its performance may vary when applied to other tasks.
58
+ - Users interested in employing this model for different tasks should explore fine-tuned versions available in the model hub for optimal results.
59
 
60
  ## Training Data
61