update model card README.md

This commit is contained in:
Sayak Paul 2022-11-11 05:49:31 +00:00
parent 32f325c957
commit 8e3538eeb0
1 changed files with 68 additions and 0 deletions

68
README.md Normal file
View File

@ -0,0 +1,68 @@
---
license: apache-2.0
tags:
- vision
- depth-estimation
- generated_from_trainer
model-index:
- name: glpn-nyu-finetuned-diode
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# glpn-nyu-finetuned-diode
This model is a fine-tuned version of [vinvino02/glpn-nyu](https://huggingface.co/vinvino02/glpn-nyu) on the diode-subset dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8193
- Rmse: 0.8077
## 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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log | 1.0 | 10 | 0.9152 | nan |
| 0.8958 | 2.0 | 20 | 0.8413 | nan |
| 0.8958 | 3.0 | 30 | 0.7873 | 1.0697 |
| 0.7472 | 4.0 | 40 | 0.7405 | 0.9340 |
| 0.7472 | 5.0 | 50 | 0.7017 | 0.8441 |
| 0.6999 | 6.0 | 60 | 0.6785 | 0.7959 |
| 0.6999 | 7.0 | 70 | 0.6656 | 0.7672 |
| 0.6917 | 8.0 | 80 | 0.6490 | 0.7413 |
| 0.6917 | 9.0 | 90 | 0.6413 | 0.7212 |
| 0.6527 | 10.0 | 100 | 0.6408 | 0.7146 |
### Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Tokenizers 0.13.2