sayakpaul/glpn-nyu-finetuned-diode is a forked repo from huggingface. License: apache-2-0
Go to file
Sayak Paul 382b9486c1 update model card README.md 2022-11-11 06:07:13 +00:00
runs End of training 2022-11-11 06:03:38 +00:00
.gitattributes initial commit 2022-11-11 05:40:02 +00:00
.gitignore Training in progress, epoch 1 2022-11-11 05:40:46 +00:00
README.md update model card README.md 2022-11-11 06:07:13 +00:00
config.json Training in progress, epoch 1 2022-11-11 05:40:46 +00:00
preprocessor_config.json Training in progress, epoch 1 2022-11-11 05:40:46 +00:00
pytorch_model.bin End of training 2022-11-11 06:03:38 +00:00
training_args.bin Training in progress, epoch 1 2022-11-11 05:57:22 +00:00

README.md

license tags model-index
apache-2.0
vision
depth-estimation
generated_from_trainer
name results
glpn-nyu-finetuned-diode

glpn-nyu-finetuned-diode

This model is a fine-tuned version of vinvino02/glpn-nyu on the diode-subset dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4359
  • Rmse: 0.4276

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: 2e-05
  • train_batch_size: 24
  • eval_batch_size: 24
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rmse
No log 1.0 13 1.2498 0.9726
0.8469 2.0 26 1.0661 nan
0.8469 3.0 39 0.9959 0.5287
0.6946 4.0 52 0.8550 0.4084
0.586 5.0 65 0.7679 0.3603
0.586 6.0 78 0.6650 0.3119
0.5195 7.0 91 0.6837 0.3370
0.4737 8.0 104 0.6638 0.3366
0.4737 9.0 117 0.6522 0.3250
0.4663 10.0 130 0.6461 0.3153

Framework versions

  • Transformers 4.24.0
  • Pytorch 1.12.1+cu113
  • Tokenizers 0.13.2