Commit
•
3a092cb
1
Parent(s):
ff0e12a
Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-tiny-1k-224
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnextv2-tiny-1k-224-finetuned-cassava-leaf-disease
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: train
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8649532710280374
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# convnextv2-tiny-1k-224-finetuned-cassava-leaf-disease
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4109
|
| 36 |
+
- Accuracy: 0.8650
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 5e-05
|
| 56 |
+
- train_batch_size: 480
|
| 57 |
+
- eval_batch_size: 480
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 1920
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 15
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 7.8796 | 0.98 | 10 | 3.9572 | 0.1706 |
|
| 71 |
+
| 2.3762 | 1.95 | 20 | 1.4334 | 0.6178 |
|
| 72 |
+
| 1.1413 | 2.93 | 30 | 0.8877 | 0.6841 |
|
| 73 |
+
| 0.7549 | 4.0 | 41 | 0.6403 | 0.7724 |
|
| 74 |
+
| 0.5904 | 4.98 | 51 | 0.5366 | 0.8098 |
|
| 75 |
+
| 0.5152 | 5.95 | 61 | 0.4799 | 0.8369 |
|
| 76 |
+
| 0.4764 | 6.93 | 71 | 0.4567 | 0.8486 |
|
| 77 |
+
| 0.4386 | 8.0 | 82 | 0.4421 | 0.8509 |
|
| 78 |
+
| 0.4306 | 8.98 | 92 | 0.4381 | 0.8519 |
|
| 79 |
+
| 0.4266 | 9.95 | 102 | 0.4296 | 0.8603 |
|
| 80 |
+
| 0.4072 | 10.93 | 112 | 0.4196 | 0.8593 |
|
| 81 |
+
| 0.4033 | 12.0 | 123 | 0.4127 | 0.8621 |
|
| 82 |
+
| 0.3982 | 12.98 | 133 | 0.4125 | 0.8640 |
|
| 83 |
+
| 0.3993 | 13.95 | 143 | 0.4097 | 0.8631 |
|
| 84 |
+
| 0.3812 | 14.63 | 150 | 0.4109 | 0.8650 |
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
### Framework versions
|
| 88 |
+
|
| 89 |
+
- Transformers 4.37.2
|
| 90 |
+
- Pytorch 2.2.1
|
| 91 |
+
- Datasets 2.18.0
|
| 92 |
+
- Tokenizers 0.15.1
|