update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- imagefolder
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: blurred_landmarks
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: imagefolder
|
| 17 |
+
type: imagefolder
|
| 18 |
+
config: landmarks
|
| 19 |
+
split: validation
|
| 20 |
+
args: landmarks
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.9645365168539326
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# blurred_landmarks
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.1152
|
| 35 |
+
- Accuracy: 0.9645
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 8
|
| 56 |
+
- eval_batch_size: 8
|
| 57 |
+
- seed: 42
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 32
|
| 60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
+
- lr_scheduler_type: linear
|
| 62 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 63 |
+
- num_epochs: 20
|
| 64 |
+
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 69 |
+
| 0.6588 | 1.0 | 357 | 0.6460 | 0.7707 |
|
| 70 |
+
| 0.3752 | 2.0 | 714 | 0.2969 | 0.8933 |
|
| 71 |
+
| 0.3275 | 3.0 | 1071 | 0.1912 | 0.9319 |
|
| 72 |
+
| 0.2183 | 4.0 | 1429 | 0.1794 | 0.9305 |
|
| 73 |
+
| 0.2133 | 5.0 | 1786 | 0.1638 | 0.9414 |
|
| 74 |
+
| 0.1984 | 6.0 | 2143 | 0.1322 | 0.9484 |
|
| 75 |
+
| 0.1409 | 7.0 | 2500 | 0.1304 | 0.9529 |
|
| 76 |
+
| 0.1864 | 8.0 | 2858 | 0.1212 | 0.9572 |
|
| 77 |
+
| 0.1778 | 9.0 | 3215 | 0.1216 | 0.9540 |
|
| 78 |
+
| 0.1734 | 10.0 | 3572 | 0.1129 | 0.9593 |
|
| 79 |
+
| 0.1349 | 11.0 | 3929 | 0.1127 | 0.9614 |
|
| 80 |
+
| 0.1057 | 12.0 | 4287 | 0.1177 | 0.9582 |
|
| 81 |
+
| 0.1434 | 13.0 | 4644 | 0.1153 | 0.9603 |
|
| 82 |
+
| 0.0832 | 14.0 | 5001 | 0.1264 | 0.9593 |
|
| 83 |
+
| 0.0963 | 15.0 | 5358 | 0.1146 | 0.9607 |
|
| 84 |
+
| 0.0642 | 16.0 | 5716 | 0.1135 | 0.9635 |
|
| 85 |
+
| 0.0763 | 17.0 | 6073 | 0.1210 | 0.9614 |
|
| 86 |
+
| 0.0432 | 18.0 | 6430 | 0.1162 | 0.9645 |
|
| 87 |
+
| 0.0618 | 19.0 | 6787 | 0.1269 | 0.9600 |
|
| 88 |
+
| 0.049 | 19.99 | 7140 | 0.1152 | 0.9645 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.30.0.dev0
|
| 94 |
+
- Pytorch 1.13.0
|
| 95 |
+
- Datasets 2.10.1
|
| 96 |
+
- Tokenizers 0.11.0
|