End of training
Browse files
README.md
CHANGED
|
@@ -4,9 +4,26 @@ license: apache-2.0
|
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: lettuce-npk-vit
|
| 9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,7 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abdoulaye-diop/lettuce-npk-deficiency-prediction/runs/at88jlqw)
|
| 17 |
# lettuce-npk-vit
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -46,6 +66,27 @@ The following hyperparameters were used during training:
|
|
| 46 |
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
- num_epochs: 20
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.44.2
|
|
|
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- imagefolder
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
model-index:
|
| 12 |
- name: lettuce-npk-vit
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Image Classification
|
| 16 |
+
type: image-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: imagefolder
|
| 19 |
+
type: imagefolder
|
| 20 |
+
config: default
|
| 21 |
+
split: train
|
| 22 |
+
args: default
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 0.8095238095238095
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 33 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abdoulaye-diop/lettuce-npk-deficiency-prediction/runs/at88jlqw)
|
| 34 |
# lettuce-npk-vit
|
| 35 |
|
| 36 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.7449
|
| 39 |
+
- Accuracy: 0.8095
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 66 |
- lr_scheduler_warmup_ratio: 0.1
|
| 67 |
- num_epochs: 20
|
| 68 |
|
| 69 |
+
### Training results
|
| 70 |
+
|
| 71 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 72 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 73 |
+
| No log | 0.7273 | 2 | 1.3774 | 0.2143 |
|
| 74 |
+
| No log | 1.8182 | 5 | 1.2738 | 0.4524 |
|
| 75 |
+
| No log | 2.9091 | 8 | 1.1874 | 0.6190 |
|
| 76 |
+
| 1.2511 | 4.0 | 11 | 1.1162 | 0.7619 |
|
| 77 |
+
| 1.2511 | 4.7273 | 13 | 1.0780 | 0.7143 |
|
| 78 |
+
| 1.2511 | 5.8182 | 16 | 1.0037 | 0.7857 |
|
| 79 |
+
| 1.2511 | 6.9091 | 19 | 0.9342 | 0.8095 |
|
| 80 |
+
| 0.9308 | 8.0 | 22 | 0.8653 | 0.8095 |
|
| 81 |
+
| 0.9308 | 8.7273 | 24 | 0.8485 | 0.8095 |
|
| 82 |
+
| 0.9308 | 9.8182 | 27 | 0.8264 | 0.8333 |
|
| 83 |
+
| 0.7204 | 10.9091 | 30 | 0.8243 | 0.7857 |
|
| 84 |
+
| 0.7204 | 12.0 | 33 | 0.7299 | 0.8571 |
|
| 85 |
+
| 0.7204 | 12.7273 | 35 | 0.7376 | 0.8095 |
|
| 86 |
+
| 0.7204 | 13.8182 | 38 | 0.7358 | 0.8333 |
|
| 87 |
+
| 0.6101 | 14.5455 | 40 | 0.7449 | 0.8095 |
|
| 88 |
+
|
| 89 |
+
|
| 90 |
### Framework versions
|
| 91 |
|
| 92 |
- Transformers 4.44.2
|