Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,26 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
tags:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for tmp-pl-image-classification
|
| 7 |
|
| 8 |
-
์ด ์ ์ฅ์๋ ๐ค Transformers์ `pipeline()` ๋์์ ์ดํดํ๊ณ ์ฐ์ตํ๊ธฐ ์ํ **ํ์ต์ฉ(pipeline practice) ๋ชจ๋ธ repo
|
| 9 |
-
๋ชจ๋ธ ๊ฐ์ค์น๋ ์๋ณธ ๋ชจ๋ธ **`google/vit-base-patch16-224
|
| 10 |
|
| 11 |
---
|
| 12 |
|
|
@@ -62,8 +76,6 @@ Hub์ ์
๋ก๋ํ๊ณ ๋ค์ ๋ถ๋ฌ์ค๋ ์ ์ฒด ํ๋ฆ์ ์ค์ตํ๊ธฐ ์ํด
|
|
| 62 |
- ์ค์ ์๋น์ค ํ๊ฒฝ์์์ ๋ชจ๋ธ ๋ฐฐํฌ
|
| 63 |
- ํน์ ๋๋ฉ์ธ(์๋ฃ, ์ฐ์
์์ ๋ฑ)์ ๋ํ ์ ๋ขฐ์ฑ ์๋ ์ถ๋ก
|
| 64 |
|
| 65 |
-
[More Information Needed]
|
| 66 |
-
|
| 67 |
## Bias, Risks, and Limitations
|
| 68 |
|
| 69 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
|
@@ -72,8 +84,6 @@ Hub์ ์
๋ก๋ํ๊ณ ๋ค์ ๋ถ๋ฌ์ค๋ ์ ์ฒด ํ๋ฆ์ ์ค์ตํ๊ธฐ ์ํด
|
|
| 72 |
- ํน์ ๊ฐ์ฒด, ๋ฌธํ์ ๋งฅ๋ฝ, ์ ๋ฌธ ๋๋ฉ์ธ์ ๋ํ ๋ถ๋ฅ ์ฑ๋ฅ์ ๋ณด์ฅ๋์ง ์์ต๋๋ค.
|
| 73 |
- ๋ณธ repo๋ **์ฐ์ต์ฉ pipeline ์ ์ฅ์**์ด๋ฏ๋ก ๋ชจ๋ธ์ ์ฌํ์ ์ํฅ์ด๋ ํธํฅ ๋ถ์์ ๋ชฉ์ ์ผ๋ก ํ์ง ์์ต๋๋ค.
|
| 74 |
|
| 75 |
-
[More Information Needed]
|
| 76 |
-
|
| 77 |
### Recommendations
|
| 78 |
|
| 79 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
|
@@ -116,7 +126,6 @@ print(clf(image))
|
|
| 116 |
* ๋ณธ repo์์๋ **์ถ๊ฐ ํ์ต์ ์ํํ์ง ์์์ต๋๋ค.**
|
| 117 |
* ์๋ณธ ๋ชจ๋ธ์ ImageNet-21k๋ก ์ฌ์ ํ์ต(pretraining) ํ ImageNet-1k๋ก fine-tuning๋ ๋ชจ๋ธ์
๋๋ค.
|
| 118 |
|
| 119 |
-
[More Information Needed]
|
| 120 |
|
| 121 |
### Training Procedure
|
| 122 |
|
|
@@ -140,7 +149,6 @@ print(clf(image))
|
|
| 140 |
|
| 141 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 142 |
|
| 143 |
-
[More Information Needed]
|
| 144 |
|
| 145 |
## Evaluation
|
| 146 |
|
|
@@ -205,7 +213,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 205 |
* Vision Transformer (ViT-Base, patch size 16, input resolution 224x224)
|
| 206 |
* Objective: Image classification
|
| 207 |
|
| 208 |
-
[More Information Needed]
|
| 209 |
|
| 210 |
### Compute Infrastructure
|
| 211 |
|
|
@@ -214,7 +221,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 214 |
#### Hardware
|
| 215 |
|
| 216 |
* ํด๋น์์ (ํ์ต ๋ฏธ์ํ)
|
| 217 |
-
[More Information Needed]
|
| 218 |
|
| 219 |
#### Software
|
| 220 |
|
|
@@ -241,7 +247,6 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 241 |
}
|
| 242 |
```
|
| 243 |
|
| 244 |
-
[More Information Needed]
|
| 245 |
|
| 246 |
**APA:**
|
| 247 |
|
|
@@ -261,10 +266,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 261 |
|
| 262 |
* dsaint31 (pipeline practice repository)
|
| 263 |
|
| 264 |
-
[More Information Needed]
|
| 265 |
|
| 266 |
## Model Card Contact
|
| 267 |
|
| 268 |
* Hugging Face profile: [https://huggingface.co/dsaint31](https://huggingface.co/dsaint31)
|
| 269 |
-
|
| 270 |
-
[More Information Needed]
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- transformers
|
| 5 |
+
- pipeline
|
| 6 |
+
- vision
|
| 7 |
+
- image-classification
|
| 8 |
+
- vit
|
| 9 |
+
- imagenet-1k
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- ILSVRC/imagenet-1k
|
| 13 |
+
language:
|
| 14 |
+
- ko
|
| 15 |
+
base_model:
|
| 16 |
+
- google/vit-base-patch16-224
|
| 17 |
+
pipeline_tag: image-classification
|
| 18 |
---
|
| 19 |
|
| 20 |
# Model Card for tmp-pl-image-classification
|
| 21 |
|
| 22 |
+
์ด ์ ์ฅ์๋ ๐ค Transformers์ `pipeline()` ๋์์ ์ดํดํ๊ณ ์ฐ์ตํ๊ธฐ ์ํ **ํ์ต์ฉ(pipeline practice) ๋ชจ๋ธ repo** ์
๋๋ค.
|
| 23 |
+
๋ชจ๋ธ ๊ฐ์ค์น๋ ์๋ณธ ๋ชจ๋ธ **`google/vit-base-patch16-224`** ์ ๊ทธ๋๋ก ์ฌ์ฉํ๋ฉฐ, ์ถ๊ฐ์ ์ธ fine-tuning์ ์ํํ์ง ์์์ต๋๋ค.
|
| 24 |
|
| 25 |
---
|
| 26 |
|
|
|
|
| 76 |
- ์ค์ ์๋น์ค ํ๊ฒฝ์์์ ๋ชจ๋ธ ๋ฐฐํฌ
|
| 77 |
- ํน์ ๋๋ฉ์ธ(์๋ฃ, ์ฐ์
์์ ๋ฑ)์ ๋ํ ์ ๋ขฐ์ฑ ์๋ ์ถ๋ก
|
| 78 |
|
|
|
|
|
|
|
| 79 |
## Bias, Risks, and Limitations
|
| 80 |
|
| 81 |
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
|
|
|
| 84 |
- ํน์ ๊ฐ์ฒด, ๋ฌธํ์ ๋งฅ๋ฝ, ์ ๋ฌธ ๋๋ฉ์ธ์ ๋ํ ๋ถ๋ฅ ์ฑ๋ฅ์ ๋ณด์ฅ๋์ง ์์ต๋๋ค.
|
| 85 |
- ๋ณธ repo๋ **์ฐ์ต์ฉ pipeline ์ ์ฅ์**์ด๋ฏ๋ก ๋ชจ๋ธ์ ์ฌํ์ ์ํฅ์ด๋ ํธํฅ ๋ถ์์ ๋ชฉ์ ์ผ๋ก ํ์ง ์์ต๋๋ค.
|
| 86 |
|
|
|
|
|
|
|
| 87 |
### Recommendations
|
| 88 |
|
| 89 |
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
|
|
|
| 126 |
* ๋ณธ repo์์๋ **์ถ๊ฐ ํ์ต์ ์ํํ์ง ์์์ต๋๋ค.**
|
| 127 |
* ์๋ณธ ๋ชจ๋ธ์ ImageNet-21k๋ก ์ฌ์ ํ์ต(pretraining) ํ ImageNet-1k๋ก fine-tuning๋ ๋ชจ๋ธ์
๋๋ค.
|
| 128 |
|
|
|
|
| 129 |
|
| 130 |
### Training Procedure
|
| 131 |
|
|
|
|
| 149 |
|
| 150 |
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 151 |
|
|
|
|
| 152 |
|
| 153 |
## Evaluation
|
| 154 |
|
|
|
|
| 213 |
* Vision Transformer (ViT-Base, patch size 16, input resolution 224x224)
|
| 214 |
* Objective: Image classification
|
| 215 |
|
|
|
|
| 216 |
|
| 217 |
### Compute Infrastructure
|
| 218 |
|
|
|
|
| 221 |
#### Hardware
|
| 222 |
|
| 223 |
* ํด๋น์์ (ํ์ต ๋ฏธ์ํ)
|
|
|
|
| 224 |
|
| 225 |
#### Software
|
| 226 |
|
|
|
|
| 247 |
}
|
| 248 |
```
|
| 249 |
|
|
|
|
| 250 |
|
| 251 |
**APA:**
|
| 252 |
|
|
|
|
| 266 |
|
| 267 |
* dsaint31 (pipeline practice repository)
|
| 268 |
|
|
|
|
| 269 |
|
| 270 |
## Model Card Contact
|
| 271 |
|
| 272 |
* Hugging Face profile: [https://huggingface.co/dsaint31](https://huggingface.co/dsaint31)
|
|
|
|
|
|