Resnet152-30VN

This model is a fine-tuned version of microsoft/resnet-152 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5769
  • Accuracy: 0.8353

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0003
  • train_batch_size: 64
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Accuracy Validation Loss
1.4198 1.0 275 0.7348 0.8741
0.565 2.0 550 0.8119 0.6347
0.2846 3.0 825 0.8310 0.6003
0.1727 4.0 1100 0.8410 0.6041
0.0835 5.0 1375 0.8461 0.6464
0.0534 6.0 1650 0.8565 0.6776
0.0283 7.0 1925 0.7107 0.8501
0.0186 8.0 2200 0.7066 0.8620
0.0111 9.0 2475 0.6772 0.8648
0.0096 10.0 2750 0.6898 0.8628

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
77
Safetensors
Model size
58.4M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for vuongnhathien/Resnet152-30VN

Finetuned
(8)
this model

Evaluation results