Instructions to use charuka0/acne-multilabel-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use charuka0/acne-multilabel-classifier with timm:
import timm model = timm.create_model("hf_hub:charuka0/acne-multilabel-classifier", pretrained=True) - Notebooks
- Google Colab
- Kaggle
File size: 862 Bytes
4b23bd1 | 1 2 3 4 5 6 7 | backbone,timm_name,params_M,best_val_macro_f1,val_macro_auc,val_micro_f1,val_loss,latency_ms,train_min
EfficientNet-B0,efficientnet_b0,4.013953,0.8920843642863922,0.9858378407749415,0.8793565683646113,0.3783461392613888,7.724876403808594,2.1424872120221456
EfficientNet-B3,efficientnet_b3,10.703917,0.877899907214555,0.9818892991176218,0.8750835003340013,0.38993254854393555,11.962728500366211,2.480474603176117
DenseNet121,densenet121,6.958981,0.8567976961160163,0.9794149251526196,0.8492597577388964,0.3871925822412125,15.275516510009766,1.6189859549204508
MobileNetV3-Large,mobilenetv3_large_100,4.208437,0.8482443979319815,0.9751519586206963,0.8389217619986851,0.47364217558980504,6.047344207763672,1.8233353217442831
ResNet50,resnet50,23.518277,0.6566887211634265,0.8975266867921945,0.646894236149972,0.6569560721495107,5.757780075073242,1.5356720765431722
|