update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- imagefolder
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: resnet-18
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Image Classification
|
13 |
+
type: image-classification
|
14 |
+
dataset:
|
15 |
+
name: imagefolder
|
16 |
+
type: imagefolder
|
17 |
+
config: default
|
18 |
+
split: train
|
19 |
+
args: default
|
20 |
+
metrics:
|
21 |
+
- name: Accuracy
|
22 |
+
type: accuracy
|
23 |
+
value: 0.6425188074672611
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# resnet-18
|
30 |
+
|
31 |
+
This model was trained from scratch on the imagefolder dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 0.9403
|
34 |
+
- Accuracy: 0.6425
|
35 |
+
|
36 |
+
## Model description
|
37 |
+
|
38 |
+
More information needed
|
39 |
+
|
40 |
+
## Intended uses & limitations
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Training and evaluation data
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training procedure
|
49 |
+
|
50 |
+
### Training hyperparameters
|
51 |
+
|
52 |
+
The following hyperparameters were used during training:
|
53 |
+
- learning_rate: 5e-05
|
54 |
+
- train_batch_size: 32
|
55 |
+
- eval_batch_size: 32
|
56 |
+
- seed: 42
|
57 |
+
- gradient_accumulation_steps: 4
|
58 |
+
- total_train_batch_size: 128
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_ratio: 0.1
|
62 |
+
- num_epochs: 10
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
68 |
+
| 1.4726 | 1.0 | 252 | 1.3072 | 0.5068 |
|
69 |
+
| 1.2683 | 2.0 | 505 | 1.0996 | 0.5865 |
|
70 |
+
| 1.2177 | 3.0 | 757 | 1.0444 | 0.6096 |
|
71 |
+
| 1.1636 | 4.0 | 1010 | 1.0185 | 0.6096 |
|
72 |
+
| 1.1372 | 5.0 | 1262 | 0.9945 | 0.6205 |
|
73 |
+
| 1.113 | 6.0 | 1515 | 0.9703 | 0.6342 |
|
74 |
+
| 1.0734 | 7.0 | 1767 | 0.9574 | 0.6333 |
|
75 |
+
| 1.0501 | 8.0 | 2020 | 0.9503 | 0.6375 |
|
76 |
+
| 1.0361 | 9.0 | 2272 | 0.9488 | 0.6389 |
|
77 |
+
| 1.0302 | 9.98 | 2520 | 0.9403 | 0.6425 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.30.0
|
83 |
+
- Pytorch 2.1.0+cu118
|
84 |
+
- Datasets 2.14.6
|
85 |
+
- Tokenizers 0.13.3
|