aaronqg/golden-foot-football-players
Viewer • Updated • 7.19k • 34
How to use omaralshareef/football-player-classifier with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-classification", model="omaralshareef/football-player-classifier")
pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png") # Load model directly
from transformers import AutoImageProcessor, AutoModelForImageClassification
processor = AutoImageProcessor.from_pretrained("omaralshareef/football-player-classifier")
model = AutoModelForImageClassification.from_pretrained("omaralshareef/football-player-classifier", device_map="auto")How to use omaralshareef/football-player-classifier with timm:
import timm
model = timm.create_model("hf_hub:omaralshareef/football-player-classifier", pretrained=True)Fine-tuned ResNet-50 on aaronqg/golden-foot-football-players.
Given a photo of a footballer, the model predicts which Golden Foot winner or nominee it is.
Alessandro Del Piero, Andrés Iniesta, Andriy Shevchenko, Cristiano Ronaldo, Didier Drogba, Diego Maradona, Edinson Cavani, Francesco Totti, Gianluigi Buffon, Iker Casillas, Lionel Messi, Luka Modrić, Mohamed Salah, Pavel Nedvěd, Pelé, Ryan Giggs, Roberto Baggio, Roberto Carlos, Ronaldinho, Ronaldo Nazário, Samuel Eto'o, Zlatan Ibrahimović.
| Split | Accuracy | Macro F1 |
|---|---|---|
| Validation (best) | 72.8% | 72.7% |
| Test | 74.1% | 73.8% |
from transformers import pipeline
clf = pipeline("image-classification", model="omaralshareef/football-player-classifier")
print(clf("player.jpg"))
Base model
timm/resnet50.a1_in1k