Hugging Face's logo

Library-Mutsumi
/
clip_onnx

Zero-Shot Classification
ONNX
Transformers
English
dghs-realutils
clip
image
Model card Files
xet
 Community
Plana-Archive commited on
Commit
04e67ca
·
verified ·
1 Parent(s): 291c75b

Migrasi final otomatis

Browse files
Files changed (22) hide show
  1. README.md +30 -0
  2. models.parquet +3 -0
  3. openai/clip-vit-base-patch16/image_encode.onnx +3 -0
  4. openai/clip-vit-base-patch16/meta.json +15 -0
  5. openai/clip-vit-base-patch16/preprocessor.json +38 -0
  6. openai/clip-vit-base-patch16/text_encode.onnx +3 -0
  7. openai/clip-vit-base-patch16/tokenizer.json +0 -0
  8. openai/clip-vit-base-patch32/image_encode.onnx +3 -0
  9. openai/clip-vit-base-patch32/meta.json +15 -0
  10. openai/clip-vit-base-patch32/preprocessor.json +38 -0
  11. openai/clip-vit-base-patch32/text_encode.onnx +3 -0
  12. openai/clip-vit-base-patch32/tokenizer.json +0 -0
  13. openai/clip-vit-large-patch14-336/image_encode.onnx +3 -0
  14. openai/clip-vit-large-patch14-336/meta.json +15 -0
  15. openai/clip-vit-large-patch14-336/preprocessor.json +38 -0
  16. openai/clip-vit-large-patch14-336/text_encode.onnx +3 -0
  17. openai/clip-vit-large-patch14-336/tokenizer.json +0 -0
  18. openai/clip-vit-large-patch14/image_encode.onnx +3 -0
  19. openai/clip-vit-large-patch14/meta.json +15 -0
  20. openai/clip-vit-large-patch14/preprocessor.json +38 -0
  21. openai/clip-vit-large-patch14/text_encode.onnx +3 -0
  22. openai/clip-vit-large-patch14/tokenizer.json +0 -0
README.md ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: zero-shot-classification
3
+ base_model:
4
+ - openai/clip-vit-base-patch16
5
+ - openai/clip-vit-base-patch32
6
+ - openai/clip-vit-large-patch14
7
+ - openai/clip-vit-large-patch14-336
8
+ language:
9
+ - en
10
+ tags:
11
+ - transformers
12
+ - clip
13
+ - image
14
+ - dghs-realutils
15
+ library_name: dghs-realutils
16
+ ---
17
+
18
+ ONNX exported version of CLIP models.
19
+
20
+ # Models
21
+
22
+ 4 models exported in total.
23
+
24
+ | Name | Image (Params/FLOPS) | Image Size | Image Width (Enc/Emb) | Text (Params/FLOPS) | Text Width (Enc/Emb) | Created At |
25
+ |:----------------------------------------------------------------------------------------------|:-----------------------|-------------:|:------------------------|:----------------------|:-----------------------|:-------------|
26
+ | [openai/clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) | 302.9M / 174.7G | 336 | 1024 / 768 | 85.1M / 1.2G | 768 / 768 | 2022-04-22 |
27
+ | [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) | 302.9M / 77.8G | 224 | 1024 / 768 | 85.1M / 1.2G | 768 / 768 | 2022-03-03 |
28
+ | [openai/clip-vit-base-patch16](https://huggingface.co/openai/clip-vit-base-patch16) | 85.6M / 16.9G | 224 | 768 / 512 | 37.8M / 529.2M | 512 / 512 | 2022-03-03 |
29
+ | [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) | 87.4M / 4.4G | 224 | 768 / 512 | 37.8M / 529.2M | 512 / 512 | 2022-03-03 |
30
+
models.parquet ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9150f4745be893a842e26063ef95cc47aed9155eb2d3de7b8830c5cc8bb9e9af
3
+ size 8637
openai/clip-vit-base-patch16/image_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9546aaa4e94c5ac85cb64ca74729eca7343d0c690744d746a9a0dc25907c639
3
+ size 345024893
openai/clip-vit-base-patch16/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_embedding_width": 512,
3
+ "image_encoding_width": 768,
4
+ "image_flops": 16862865408.0,
5
+ "image_params": 85647360.0,
6
+ "image_size": 224,
7
+ "logit_scale": 4.605170249938965,
8
+ "name": "clip-vit-base-patch16",
9
+ "repo_created_at": 1646263745.0,
10
+ "repo_id": "openai/clip-vit-base-patch16",
11
+ "text_embedding_width": 512,
12
+ "text_encoding_width": 512,
13
+ "text_flops": 529199104.0,
14
+ "text_params": 37829632.0
15
+ }
openai/clip-vit-base-patch16/preprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stages": [
3
+ {
4
+ "force_background": "white",
5
+ "type": "convert_rgb"
6
+ },
7
+ {
8
+ "antialias": true,
9
+ "interpolation": "bicubic",
10
+ "max_size": null,
11
+ "size": 224,
12
+ "type": "resize"
13
+ },
14
+ {
15
+ "size": [
16
+ 224,
17
+ 224
18
+ ],
19
+ "type": "center_crop"
20
+ },
21
+ {
22
+ "type": "to_tensor"
23
+ },
24
+ {
25
+ "mean": [
26
+ 0.48145467042922974,
27
+ 0.45782750844955444,
28
+ 0.40821072459220886
29
+ ],
30
+ "std": [
31
+ 0.2686295509338379,
32
+ 0.2613025903701782,
33
+ 0.27577710151672363
34
+ ],
35
+ "type": "normalize"
36
+ }
37
+ ]
38
+ }
openai/clip-vit-base-patch16/text_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777bfe38c6ff9c5230fad08b9773a641f56403f4bc3d4bf639d17f3f9274536a
3
+ size 253990000
openai/clip-vit-base-patch16/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
openai/clip-vit-base-patch32/image_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58773462a749e7122def90d16eb159c20dff1f40b210f40ba834161ddd076f2e
3
+ size 351650753
openai/clip-vit-base-patch32/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_embedding_width": 512,
3
+ "image_encoding_width": 768,
4
+ "image_flops": 4366181376.0,
5
+ "image_params": 87416832.0,
6
+ "image_size": 224,
7
+ "logit_scale": 4.605170249938965,
8
+ "name": "clip-vit-base-patch32",
9
+ "repo_created_at": 1646263745.0,
10
+ "repo_id": "openai/clip-vit-base-patch32",
11
+ "text_embedding_width": 512,
12
+ "text_encoding_width": 512,
13
+ "text_flops": 529199104.0,
14
+ "text_params": 37829632.0
15
+ }
openai/clip-vit-base-patch32/preprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stages": [
3
+ {
4
+ "force_background": "white",
5
+ "type": "convert_rgb"
6
+ },
7
+ {
8
+ "antialias": true,
9
+ "interpolation": "bicubic",
10
+ "max_size": null,
11
+ "size": 224,
12
+ "type": "resize"
13
+ },
14
+ {
15
+ "size": [
16
+ 224,
17
+ 224
18
+ ],
19
+ "type": "center_crop"
20
+ },
21
+ {
22
+ "type": "to_tensor"
23
+ },
24
+ {
25
+ "mean": [
26
+ 0.48145467042922974,
27
+ 0.45782750844955444,
28
+ 0.40821072459220886
29
+ ],
30
+ "std": [
31
+ 0.2686295509338379,
32
+ 0.2613025903701782,
33
+ 0.27577710151672363
34
+ ],
35
+ "type": "normalize"
36
+ }
37
+ ]
38
+ }
openai/clip-vit-base-patch32/text_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f07758ed6a9f05f8af341a80c486fcb547db499e8a5f5c79d8bc7e38d298156
3
+ size 253990000
openai/clip-vit-base-patch32/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
openai/clip-vit-large-patch14-336/image_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2c86f35c06f13796d52c25ab3d3bc5903a5dfcdac758ac173657863971f907
3
+ size 1217674510
openai/clip-vit-large-patch14-336/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_embedding_width": 768,
3
+ "image_encoding_width": 1024,
4
+ "image_flops": 174710792192.0,
5
+ "image_params": 302915584.0,
6
+ "image_size": 336,
7
+ "logit_scale": 4.605170249938965,
8
+ "name": "clip-vit-large-patch14-336",
9
+ "repo_created_at": 1650639463.0,
10
+ "repo_id": "openai/clip-vit-large-patch14-336",
11
+ "text_embedding_width": 768,
12
+ "text_encoding_width": 768,
13
+ "text_flops": 1190160384.0,
14
+ "text_params": 85056000.0
15
+ }
openai/clip-vit-large-patch14-336/preprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stages": [
3
+ {
4
+ "force_background": "white",
5
+ "type": "convert_rgb"
6
+ },
7
+ {
8
+ "antialias": true,
9
+ "interpolation": "bicubic",
10
+ "max_size": null,
11
+ "size": 336,
12
+ "type": "resize"
13
+ },
14
+ {
15
+ "size": [
16
+ 336,
17
+ 336
18
+ ],
19
+ "type": "center_crop"
20
+ },
21
+ {
22
+ "type": "to_tensor"
23
+ },
24
+ {
25
+ "mean": [
26
+ 0.48145467042922974,
27
+ 0.45782750844955444,
28
+ 0.40821072459220886
29
+ ],
30
+ "std": [
31
+ 0.2686295509338379,
32
+ 0.2613025903701782,
33
+ 0.27577710151672363
34
+ ],
35
+ "type": "normalize"
36
+ }
37
+ ]
38
+ }
openai/clip-vit-large-patch14-336/text_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c040a8a429bae34d99fa83a1f2dd48a0f6b21ccbe878eccb7c40c30291fda6e
3
+ size 494879632
openai/clip-vit-large-patch14-336/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
openai/clip-vit-large-patch14/image_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b15a7dbd19afefb67ee5cc299e10140193c959507a381d17fcbed31f345fdbef
3
+ size 1216363788
openai/clip-vit-large-patch14/meta.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_embedding_width": 768,
3
+ "image_encoding_width": 1024,
4
+ "image_flops": 77817126912.0,
5
+ "image_params": 302915584.0,
6
+ "image_size": 224,
7
+ "logit_scale": 4.605170249938965,
8
+ "name": "clip-vit-large-patch14",
9
+ "repo_created_at": 1646263745.0,
10
+ "repo_id": "openai/clip-vit-large-patch14",
11
+ "text_embedding_width": 768,
12
+ "text_encoding_width": 768,
13
+ "text_flops": 1190160384.0,
14
+ "text_params": 85056000.0
15
+ }
openai/clip-vit-large-patch14/preprocessor.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "stages": [
3
+ {
4
+ "force_background": "white",
5
+ "type": "convert_rgb"
6
+ },
7
+ {
8
+ "antialias": true,
9
+ "interpolation": "bicubic",
10
+ "max_size": null,
11
+ "size": 224,
12
+ "type": "resize"
13
+ },
14
+ {
15
+ "size": [
16
+ 224,
17
+ 224
18
+ ],
19
+ "type": "center_crop"
20
+ },
21
+ {
22
+ "type": "to_tensor"
23
+ },
24
+ {
25
+ "mean": [
26
+ 0.48145467042922974,
27
+ 0.45782750844955444,
28
+ 0.40821072459220886
29
+ ],
30
+ "std": [
31
+ 0.2686295509338379,
32
+ 0.2613025903701782,
33
+ 0.27577710151672363
34
+ ],
35
+ "type": "normalize"
36
+ }
37
+ ]
38
+ }
openai/clip-vit-large-patch14/text_encode.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a656e1f17390c75112babfeb3963077865d0c66d2916d7be87040db428ab1c
3
+ size 494879632
openai/clip-vit-large-patch14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff