dsaint31 commited on
Commit
c262f1b
ยท
verified ยท
1 Parent(s): 878134e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -15
README.md CHANGED
@@ -1,12 +1,26 @@
1
  ---
2
  library_name: transformers
3
- tags: [transformers, pipeline, vision, image-classification, vit, imagenet-1k]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ---
5
 
6
  # Model Card for tmp-pl-image-classification
7
 
8
- ์ด ์ €์žฅ์†Œ๋Š” ๐Ÿค— Transformers์˜ `pipeline()` ๋™์ž‘์„ ์ดํ•ดํ•˜๊ณ  ์—ฐ์Šตํ•˜๊ธฐ ์œ„ํ•œ **ํ•™์Šต์šฉ(pipeline practice) ๋ชจ๋ธ repo**์ž…๋‹ˆ๋‹ค.
9
- ๋ชจ๋ธ ๊ฐ€์ค‘์น˜๋Š” ์›๋ณธ ๋ชจ๋ธ **`google/vit-base-patch16-224`**์„ ๊ทธ๋Œ€๋กœ ์‚ฌ์šฉํ•˜๋ฉฐ, ์ถ”๊ฐ€์ ์ธ fine-tuning์€ ์ˆ˜ํ–‰ํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.
10
 
11
  ---
12
 
@@ -62,8 +76,6 @@ Hub์— ์—…๋กœ๋“œํ•˜๊ณ  ๋‹ค์‹œ ๋ถˆ๋Ÿฌ์˜ค๋Š” ์ „์ฒด ํ๋ฆ„์„ ์‹ค์Šตํ•˜๊ธฐ ์œ„ํ•ด
62
  - ์‹ค์ œ ์„œ๋น„์Šค ํ™˜๊ฒฝ์—์„œ์˜ ๋ชจ๋ธ ๋ฐฐํฌ
63
  - ํŠน์ • ๋„๋ฉ”์ธ(์˜๋ฃŒ, ์‚ฐ์—… ์˜์ƒ ๋“ฑ)์— ๋Œ€ํ•œ ์‹ ๋ขฐ์„ฑ ์žˆ๋Š” ์ถ”๋ก 
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— ์—…๋กœ๋“œํ•˜๊ณ  ๋‹ค์‹œ ๋ถˆ๋Ÿฌ์˜ค๋Š” ์ „์ฒด ํ๋ฆ„์„ ์‹ค์Šตํ•˜๊ธฐ ์œ„ํ•ด
72
  - ํŠน์ • ๊ฐ์ฒด, ๋ฌธํ™”์  ๋งฅ๋ฝ, ์ „๋ฌธ ๋„๋ฉ”์ธ์— ๋Œ€ํ•œ ๋ถ„๋ฅ˜ ์„ฑ๋Šฅ์€ ๋ณด์žฅ๋˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
73
  - ๋ณธ repo๋Š” **์—ฐ์Šต์šฉ pipeline ์ €์žฅ์†Œ**์ด๋ฏ€๋กœ ๋ชจ๋ธ์˜ ์‚ฌํšŒ์  ์˜ํ–ฅ์ด๋‚˜ ํŽธํ–ฅ ๋ถ„์„์„ ๋ชฉ์ ์œผ๋กœ ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
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 repo์—์„œ๋Š” **์ถ”๊ฐ€ ํ•™์Šต์„ ์ˆ˜ํ–‰ํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.**
117
  * ์›๋ณธ ๋ชจ๋ธ์€ ImageNet-21k๋กœ ์‚ฌ์ „ํ•™์Šต(pretraining) ํ›„ ImageNet-1k๋กœ fine-tuning๋œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹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
  * ํ•ด๋‹น์—†์Œ (ํ•™์Šต ๋ฏธ์ˆ˜ํ–‰)
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 ์ €์žฅ์†Œ๋Š” ๐Ÿค— Transformers์˜ `pipeline()` ๋™์ž‘์„ ์ดํ•ดํ•˜๊ณ  ์—ฐ์Šตํ•˜๊ธฐ ์œ„ํ•œ **ํ•™์Šต์šฉ(pipeline practice) ๋ชจ๋ธ repo** ์ž…๋‹ˆ๋‹ค.
23
+ ๋ชจ๋ธ ๊ฐ€์ค‘์น˜๋Š” ์›๋ณธ ๋ชจ๋ธ **`google/vit-base-patch16-224`** ์„ ๊ทธ๋Œ€๋กœ ์‚ฌ์šฉํ•˜๋ฉฐ, ์ถ”๊ฐ€์ ์ธ fine-tuning์€ ์ˆ˜ํ–‰ํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.
24
 
25
  ---
26
 
 
76
  - ์‹ค์ œ ์„œ๋น„์Šค ํ™˜๊ฒฝ์—์„œ์˜ ๋ชจ๋ธ ๋ฐฐํฌ
77
  - ํŠน์ • ๋„๋ฉ”์ธ(์˜๋ฃŒ, ์‚ฐ์—… ์˜์ƒ ๋“ฑ)์— ๋Œ€ํ•œ ์‹ ๋ขฐ์„ฑ ์žˆ๋Š” ์ถ”๋ก 
78
 
 
 
79
  ## Bias, Risks, and Limitations
80
 
81
  <!-- This section is meant to convey both technical and sociotechnical limitations. -->
 
84
  - ํŠน์ • ๊ฐ์ฒด, ๋ฌธํ™”์  ๋งฅ๋ฝ, ์ „๋ฌธ ๋„๋ฉ”์ธ์— ๋Œ€ํ•œ ๋ถ„๋ฅ˜ ์„ฑ๋Šฅ์€ ๋ณด์žฅ๋˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
85
  - ๋ณธ repo๋Š” **์—ฐ์Šต์šฉ pipeline ์ €์žฅ์†Œ**์ด๋ฏ€๋กœ ๋ชจ๋ธ์˜ ์‚ฌํšŒ์  ์˜ํ–ฅ์ด๋‚˜ ํŽธํ–ฅ ๋ถ„์„์„ ๋ชฉ์ ์œผ๋กœ ํ•˜์ง€ ์•Š์Šต๋‹ˆ๋‹ค.
86
 
 
 
87
  ### Recommendations
88
 
89
  <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
 
126
  * ๋ณธ repo์—์„œ๋Š” **์ถ”๊ฐ€ ํ•™์Šต์„ ์ˆ˜ํ–‰ํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค.**
127
  * ์›๋ณธ ๋ชจ๋ธ์€ ImageNet-21k๋กœ ์‚ฌ์ „ํ•™์Šต(pretraining) ํ›„ ImageNet-1k๋กœ fine-tuning๋œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹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
  * ํ•ด๋‹น์—†์Œ (ํ•™์Šต ๋ฏธ์ˆ˜ํ–‰)
 
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)