FoodBev_ConvNext_Predictor

FoodBev — ConvNeXt-Base food classifier

convnext_base.fb_in1k fine-tuned on Food-101 (101 dish classes). Stage 1 of the FoodBev food-image-recognition and beverage-pairing project, a TUM Deep Learning and Decision Making course project.

Results

Measured on the Food-101 validation split (25,250 images, 250 per class), which is the standard benchmark test set. It was held out of every checkpoint and early-stopping decision and evaluated exactly once, after training finished.

Selected from a controlled 14-run comparison across four families (ConvNeXt, EfficientNet, ViT, ResNet) and three scale tiers, all trained under one shared recipe: batch size 64, 60 epochs, AdamW, ImageNet-1k-only pretraining.

Details

Files

• export.pt — weights plus the class-name list, input resolution and embedding dimension needed to rebuild the model. (upload pending)

Note on using this for pairing

Top-1 is 91.65% but top-5 is 98.47%. Roughly one photo in twelve gets the wrong dish under a hard argmax, while the correct dish is in the top-5 about sixty-four times out of sixty-five. Downstream consumers should prefer the probability distribution over the single label.