Zum Inhalt springen Studio Erstelle Bilder und Videos, ohne in der KI-Toolchain leben zu müssen.
Ein lokal-orientierter Arbeitsbereich, um ComfyUI-Workflows in Werkzeuge zu verwandeln, die Sie nutzen, verstehen und wiederverwenden können.
© 2026 Tea Time Labs
Lokale KI-Kreation, organisiert.
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation. Workflow verständlich machen. Jetzt ausprobieren ↗
ViTFERPP Vit Small Patch16 224.augreg In1k | ST Studio
Ressourcen / ViTFERPP Vit Small Patch16 224.augreg In1k ViTFERPP Vit Small Patch16 224.augreg In1k This repository contains a Vision Transformer (ViT-Small) model fine-tuned for Facial Expression Recognition (FER).
This repository contains a Vision Transformer (ViT-Small) model fine-tuned for Facial Expression Recognition (FER).
Art Other Version Revision 75c1b11
Modellquelle
Art Other
Dateigröße 82,7 MB
Version vRevision 75c1b11
Aktualisiert 21. Sept. 2026
Downloads 0
Quelle Hugging Face ViT-Small for Facial Expression Recognition (FER++)
This repository contains a Vision Transformer (ViT-Small) model fine-tuned for Facial Expression Recognition (FER) .
The model is initialized from the pretrained checkpoint vit_small_patch16_224.augreg_in1k from the timm library and fine-tuned on a 7-class emotion classification dataset (aligned with FER++ taxonomy).
Model Details
Modellartefakte
1 Artefakt vitsmall2.pth
pth · 82,7 MB · SHA-256 bc3993eb6db7…ff42 · Hugging Face
Herunterladen
Model Architecture: Vision Transformer (ViT-Small)Pretrained Base: vit_small_patch16_224.augreg_in1kNumber of Parameters: ~22MTask: 7-class Facial Expression ClassificationClasses:
0: Angry1: Disgust2: Fear3: Happy4: Neutral5: Sad6: Surprise
Training Parameters & Hyperparameters The model was fine-tuned using PyTorch and the timm library with the following setup:
Hyperparameter Value Epochs 50 Batch Size 128 Base Learning Rate 5e-4 Weight Decay 0.01 Optimizer AdamW Scheduler Cosine Annealing (with 5-epoch warmup starting at 1e-6, min LR 1e-5) Image Resolution 224 x 224 (Bicubic Interpolation) Stochastic Depth (Drop Path) 0.1 Precision Mixed Precision (AMP) Data Augmentations RandAugment, Random Erasing (p=0.1)
Evaluation Results
Validation Set Performance
Accuracy: 83.83%Precision (Macro): 0.7892Recall (Macro): 0.7767F1-Score (Macro): 0.7817F1-Score (Weighted): 0.8378
Per-Class Validation Metrics: Class ID Class Name Precision Recall F1-Score Support 3 Happy 0.9247 0.9345 0.9295 473 6 Surprise 0.8636 0.7661 0.8120 124 4 Neutral 0.7943 0.8145 0.8043 275 0 Angry 0.7412 0.8400 0.7875 75 5 Sad
Test Set Performance
Accuracy: 83.68%Precision (Macro): 0.7800Recall (Macro): 0.7413F1-Score (Macro): 0.7565F1-Score (Weighted): 0.8348
Per-Class Test Metrics: Class ID Class Name Precision Recall F1-Score Support 3 Happy 0.9187 0.9378 0.9281 482 6 Surprise 0.8793 0.7969 0.8361 128 0 Angry 0.8158 0.8493 0.8322 73 5 Sad 0.8688 0.7277 0.7920 191 4 Neutral
How to Use Here is how you can load the model and run inference on an image using PyTorch and timm:
import torch
import torch.nn as nn
from torchvision import transforms
from PIL import Image
from timm import create_model
# Define class mapping
class_mapping = {
0: "Angry",
1: "Disgust",
2: "Fear",
3: "Happy",
4: "Neutral",
5: "Sad",
6: "Surprise"
}
# 1. Define image preprocessing matching validation/test set config
transform = transforms.Compose([
transforms.Resize((224, 224), interpolation=transforms.InterpolationMode.BICUBIC),
transforms.ToTensor(),
transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
])
# 2. Instantiate and build the model structure
model = create_model('vit_small_patch16_224.augreg_in1k', pretrained=False, num_classes=7)
# 3. Load weight state dictionary
state_dict = torch.load('vitsmall2.pth', map_location='cpu')
# Clean state_dict if it was saved using DataParallel (remove 'module.' prefix)
if list(state_dict.keys())[0].startswith('module.'):
state_dict = {k.replace('module.', ''): v for k, v in state_dict.items()}
model.load_state_dict(state_dict)
model.eval()
# 4. Perform Inference
image_path = "path_to_facial_image.jpg"
image = Image.open(image_path).convert('RGB')
input_tensor = transform(image).unsqueeze(0) # Add batch dimension
with torch.no_grad():
outputs = model(input_tensor)
probabilities = torch.softmax(outputs, dim=1)[0]
predicted_class_id = torch.argmax(probabilities).item()
print(f"Predicted emotion: {class_mapping[predicted_class_id]} ({probabilities[predicted_class_id].item():.2%})")
---
library_name: timm
tags:
- vision
- image-classification
- facial-expression-recognition
- vit
- vision-transformer
- fer
- ferplus
datasets:
- ferplus
metrics:
- accuracy
- f1
- precision
- recall
pipeline_tag: image-classification
---
# ViT-Small for Facial Expression Recognition (FER++)
This repository contains a **Vision Transformer (ViT-Small)** model fine-tuned for **Facial Expression Recognition (FER)**.
The model is initialized from the pretrained checkpoint `vit_small_patch16_224.augreg_in1k` from the `timm` library and fine-tuned on a 7-class emotion classification dataset (aligned with FER++ taxonomy).
## Model Details
- **Model Architecture:** Vision Transformer (ViT-Small)
- **Pretrained Base:** `vit_small_patch16_224.augreg_in1k`
- **Number of Parameters:** ~22M
- **Task:** 7-class Facial Expression Classification
- **Classes:**
- `0`: Angry
- `1`: Disgust
- `2`: Fear
- `3`: Happy
- `4`: Neutral
- `5`: Sad
- `6`: Surprise
## Training Parameters & Hyperparameters
The model was fine-tuned using PyTorch and the `timm` library with the following setup:
| Hyperparameter | Value |
| :--- | :--- |
| **Epochs** | 50 |
| **Batch Size** | 128 |
| **Base Learning Rate** | 5e-4 |
| **Weight Decay** | 0.01 |
| **Optimizer** | AdamW |
| **Scheduler** | Cosine Annealing (with 5-epoch warmup starting at 1e-6, min LR 1e-5) |
| **Image Resolution** | 224 x 224 (Bicubic Interpolation) |
| **Stochastic Depth (Drop Path)** | 0.1 |
| **Precision** | Mixed Precision (AMP) |
| **Data Augmentations** | RandAugment, Random Erasing (p=0.1) |
| **Loss Function** | Weighted Cross-Entropy Loss |
| **Class Weights** | `[1.560, 3.737, 2.242, 0.541, 0.527, 0.970, 1.149]` (mapping to classes 0 to 6) |
---
## Evaluation Results
### Validation Set Performance
- **Accuracy:** 83.83%
- **Precision (Macro):** 0.7892
- **Recall (Macro):** 0.7767
- **F1-Score (Macro):** 0.7817
- **F1-Score (Weighted):** 0.8378
#### Per-Class Validation Metrics:
| Class ID | Class Name | Precision | Recall | F1-Score | Support |
| :---: | :--- | :---: | :---: | :---: | :---: |
| 3 | Happy | 0.9247 | 0.9345 | 0.9295 | 473 |
| 6 | Surprise | 0.8636 | 0.7661 | 0.8120 | 124 |
| 4 | Neutral | 0.7943 | 0.8145 | 0.8043 | 275 |
| 0 | Angry | 0.7412 | 0.8400 | 0.7875 | 75 |
| 5 | Sad | 0.7758 | 0.7711 | 0.7734 | 166 |
| 2 | Fear | 0.8000 | 0.7273 | 0.7619 | 33 |
| 1 | Disgust | 0.6250...
Source context: 0 downloads · 0 likes · Pipeline image-classification · Library timm · Repo peepeeyanto/ViTFERPP_vit_small_patch16_224.augreg_in1k
Loss Function
Weighted Cross-Entropy Loss
Class Weights [1.560, 3.737, 2.242, 0.541, 0.527, 0.970, 1.149] (mapping to classes 0 to 6)
2 Fear 0.8000 0.7273 0.7619 33
1 Disgust 0.6250 0.5833 0.6034 60
2 Fear 0.6471 0.5000 0.5641 22
1 Disgust 0.6066 0.5068 0.5522 73
