Model save
Browse files- README.md +93 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-base-22k-384
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: convnextv2-base-22k-384-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: 0.8785046728971962
|
| 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-base-22k-384-finetuned-cassava-leaf-disease
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.3755
|
| 36 |
+
- Accuracy: 0.8785
|
| 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: 140
|
| 57 |
+
- eval_batch_size: 140
|
| 58 |
+
- seed: 42
|
| 59 |
+
- gradient_accumulation_steps: 4
|
| 60 |
+
- total_train_batch_size: 560
|
| 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: 16
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 0.7713 | 0.99 | 34 | 0.5754 | 0.7949 |
|
| 71 |
+
| 0.3953 | 2.0 | 69 | 0.3769 | 0.8650 |
|
| 72 |
+
| 0.3478 | 2.99 | 103 | 0.3717 | 0.8673 |
|
| 73 |
+
| 0.3296 | 4.0 | 138 | 0.3696 | 0.8752 |
|
| 74 |
+
| 0.3058 | 4.99 | 172 | 0.3387 | 0.8808 |
|
| 75 |
+
| 0.2791 | 6.0 | 207 | 0.3480 | 0.8804 |
|
| 76 |
+
| 0.2541 | 6.99 | 241 | 0.3483 | 0.8799 |
|
| 77 |
+
| 0.247 | 8.0 | 276 | 0.3590 | 0.8743 |
|
| 78 |
+
| 0.2395 | 8.99 | 310 | 0.3505 | 0.8794 |
|
| 79 |
+
| 0.2139 | 10.0 | 345 | 0.3702 | 0.8766 |
|
| 80 |
+
| 0.2116 | 10.99 | 379 | 0.3702 | 0.8766 |
|
| 81 |
+
| 0.204 | 12.0 | 414 | 0.3661 | 0.8762 |
|
| 82 |
+
| 0.183 | 12.99 | 448 | 0.3705 | 0.8776 |
|
| 83 |
+
| 0.1856 | 14.0 | 483 | 0.3861 | 0.8780 |
|
| 84 |
+
| 0.1641 | 14.99 | 517 | 0.3758 | 0.8766 |
|
| 85 |
+
| 0.1784 | 15.77 | 544 | 0.3755 | 0.8785 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- Transformers 4.39.3
|
| 91 |
+
- Pytorch 2.2.1
|
| 92 |
+
- Datasets 2.18.0
|
| 93 |
+
- Tokenizers 0.15.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 350837748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bcdd4d1c068ec9097bde950198f50e5cc382e5e7970cd6500a4237a8febcdc
|
| 3 |
size 350837748
|