results

This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12-192-22k on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5248
• Accuracy: 0.6505

Model description

On ADE20K Dataset, do image classification.

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.8495	1.0	158	2.3313	0.5525
1.8825	2.0	316	1.6815	0.623
1.4956	3.0	474	1.5248	0.6505

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.2