Hugging Face's logo

mzhaoshuai
/
CLIP4STR

English
Model card Files Community
mzhaoshuai commited on
Commit
a70545b
·
verified ·
1 Parent(s): 0fcbd88

Upload CLIP4STR Pre-trained on DataComp-1B, LAION-2B, and DFN-5B

Browse files
Files changed (8) hide show
  1. clip4str_base_6e9fe947ac.pt +3 -0
  2. clip4str_base_6e9fe947ac_log.txt +43 -0
  3. clip4str_huge_3e942729b1.pt +3 -0
  4. clip4str_huge_3e942729b1_log.txt +43 -0
  5. clip4str_huge_5eef9f86e2.pt +3 -0
  6. clip4str_huge_5eef9f86e2_log.txt +43 -0
  7. clip4str_large_3c9d881b88.pt +3 -0
  8. clip4str_large_3c9d881b88_log.txt +43 -0
clip4str_base_6e9fe947ac.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f9c480e8db69cf8c7436d918dc3867e9055234f2f55f4c2de31cf0cc6b119c
3
+ size 633162005
clip4str_base_6e9fe947ac_log.txt ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Benchmark (Subset) set:
2
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
3
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
4
+ | IIIT5k | 3000 | 99.50 | 99.88 | 97.98 | 5.09 |
5
+ | SVT | 647 | 98.30 | 99.59 | 97.05 | 5.86 |
6
+ | IC13_1015 | 1015 | 98.62 | 99.59 | 97.81 | 5.32 |
7
+ | IC15_1811 | 1811 | 91.39 | 97.19 | 95.21 | 5.38 |
8
+ | IC15_2077 | 2077 | 91.14 | 96.97 | 94.71 | 5.33 |
9
+ | SVTP | 645 | 97.98 | 99.50 | 96.99 | 5.87 |
10
+ | CUTE80 | 288 | 98.96 | 99.36 | 98.09 | 5.53 |
11
+ | HOST | 2416 | 79.30 | 94.30 | 88.73 | 5.37 |
12
+ | WOST | 2416 | 88.78 | 96.82 | 92.93 | 5.40 |
13
+ |-----------|-----------|----------|---------|------------|--------------|
14
+ | Combined | 14315 | 91.85 | 97.60 | 94.65 | 5.35 |
15
+
16
+
17
+ Benchmark set:
18
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
19
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
20
+ | IIIT5k | 3000 | 99.50 | 99.88 | 97.98 | 5.09 |
21
+ | SVT | 647 | 98.30 | 99.59 | 97.05 | 5.86 |
22
+ | IC13_1015 | 1015 | 98.62 | 99.59 | 97.81 | 5.32 |
23
+ | IC15_1811 | 1811 | 91.39 | 97.19 | 95.21 | 5.38 |
24
+ | IC15_2077 | 2077 | 91.14 | 96.97 | 94.71 | 5.33 |
25
+ | SVTP | 645 | 97.98 | 99.50 | 96.99 | 5.87 |
26
+ | CUTE80 | 288 | 98.96 | 99.36 | 98.09 | 5.53 |
27
+ | HOST | 2416 | 79.30 | 94.30 | 88.73 | 5.37 |
28
+ | WOST | 2416 | 88.78 | 96.82 | 92.93 | 5.40 |
29
+ |-----------|-----------|----------|---------|------------|--------------|
30
+ | Combined | 14315 | 91.85 | 97.60 | 94.65 | 5.35 |
31
+
32
+
33
+ New set:
34
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
35
+ |:--------:|----------:|---------:|--------:|-----------:|-------------:|
36
+ | ArT | 35149 | 85.81 | 95.34 | 93.74 | 5.41 |
37
+ | COCOv1.4 | 9825 | 81.29 | 93.94 | 88.58 | 5.92 |
38
+ | Uber | 80551 | 92.05 | 96.71 | 93.27 | 5.36 |
39
+ |----------|-----------|----------|---------|------------|--------------|
40
+ | Combined | 125525 | 89.46 | 96.11 | 93.03 | 5.42 |
41
+
42
+
43
+ Time: Total 654.3242173194885s, Average 4.6790919430741456ms. Total samples 139840.
clip4str_huge_3e942729b1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae6808c0c0af0c0b679653597c0214d0c0eb504b8d84df1ac030023b0a0215c
3
+ size 4080917077
clip4str_huge_3e942729b1_log.txt ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Benchmark (Subset) set:
2
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
3
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
4
+ | IIIT5k | 3000 | 99.53 | 99.86 | 97.82 | 5.09 |
5
+ | SVT | 647 | 99.07 | 99.78 | 97.26 | 5.86 |
6
+ | IC13_1015 | 1015 | 98.92 | 99.52 | 97.64 | 5.32 |
7
+ | IC15_1811 | 1811 | 91.72 | 97.41 | 94.43 | 5.37 |
8
+ | IC15_2077 | 2077 | 90.95 | 97.11 | 93.75 | 5.33 |
9
+ | SVTP | 645 | 97.98 | 99.46 | 96.43 | 5.86 |
10
+ | CUTE80 | 288 | 98.96 | 99.67 | 97.30 | 5.53 |
11
+ | HOST | 2416 | 82.57 | 95.34 | 87.73 | 5.38 |
12
+ | WOST | 2416 | 90.94 | 97.41 | 92.50 | 5.39 |
13
+ |-----------|-----------|----------|---------|------------|--------------|
14
+ | Combined | 14315 | 92.84 | 97.93 | 94.09 | 5.35 |
15
+
16
+
17
+ Benchmark set:
18
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
19
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
20
+ | IIIT5k | 3000 | 99.53 | 99.86 | 97.82 | 5.09 |
21
+ | SVT | 647 | 99.07 | 99.78 | 97.26 | 5.86 |
22
+ | IC13_1015 | 1015 | 98.92 | 99.52 | 97.64 | 5.32 |
23
+ | IC15_1811 | 1811 | 91.72 | 97.41 | 94.43 | 5.37 |
24
+ | IC15_2077 | 2077 | 90.95 | 97.11 | 93.75 | 5.33 |
25
+ | SVTP | 645 | 97.98 | 99.46 | 96.43 | 5.86 |
26
+ | CUTE80 | 288 | 98.96 | 99.67 | 97.30 | 5.53 |
27
+ | HOST | 2416 | 82.57 | 95.34 | 87.73 | 5.38 |
28
+ | WOST | 2416 | 90.94 | 97.41 | 92.50 | 5.39 |
29
+ |-----------|-----------|----------|---------|------------|--------------|
30
+ | Combined | 14315 | 92.84 | 97.93 | 94.09 | 5.35 |
31
+
32
+
33
+ New set:
34
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
35
+ |:--------:|----------:|---------:|--------:|-----------:|-------------:|
36
+ | ArT | 35149 | 86.41 | 95.64 | 93.20 | 5.41 |
37
+ | COCOv1.4 | 9825 | 82.96 | 94.56 | 87.63 | 5.91 |
38
+ | Uber | 80551 | 91.71 | 96.59 | 92.23 | 5.36 |
39
+ |----------|-----------|----------|---------|------------|--------------|
40
+ | Combined | 125525 | 89.54 | 96.17 | 92.14 | 5.42 |
41
+
42
+
43
+ Time: Total 4051.573532819748s, Average 28.97292286055312ms. Total samples 139840.
clip4str_huge_5eef9f86e2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d3f67d337c70d4b46a418ca296fdbe5b178f6712664872f1a1495eea248e8c
3
+ size 4080917141
clip4str_huge_5eef9f86e2_log.txt ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Benchmark (Subset) set:
2
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
3
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
4
+ | IIIT5k | 3000 | 99.67 | 99.94 | 97.54 | 5.09 |
5
+ | SVT | 647 | 98.61 | 99.64 | 96.93 | 5.87 |
6
+ | IC13_1015 | 1015 | 98.92 | 99.59 | 97.82 | 5.32 |
7
+ | IC15_1811 | 1811 | 91.61 | 97.55 | 94.25 | 5.37 |
8
+ | IC15_2077 | 2077 | 91.09 | 97.14 | 93.47 | 5.33 |
9
+ | SVTP | 645 | 98.45 | 99.61 | 96.26 | 5.86 |
10
+ | CUTE80 | 288 | 99.65 | 99.65 | 97.26 | 5.53 |
11
+ | HOST | 2416 | 80.55 | 94.82 | 86.80 | 5.37 |
12
+ | WOST | 2416 | 89.98 | 97.16 | 91.79 | 5.39 |
13
+ |-----------|-----------|----------|---------|------------|--------------|
14
+ | Combined | 14315 | 92.39 | 97.84 | 93.68 | 5.35 |
15
+
16
+
17
+ Benchmark set:
18
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
19
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
20
+ | IIIT5k | 3000 | 99.67 | 99.94 | 97.54 | 5.09 |
21
+ | SVT | 647 | 98.61 | 99.64 | 96.93 | 5.87 |
22
+ | IC13_1015 | 1015 | 98.92 | 99.59 | 97.82 | 5.32 |
23
+ | IC15_1811 | 1811 | 91.61 | 97.55 | 94.25 | 5.37 |
24
+ | IC15_2077 | 2077 | 91.09 | 97.14 | 93.47 | 5.33 |
25
+ | SVTP | 645 | 98.45 | 99.61 | 96.26 | 5.86 |
26
+ | CUTE80 | 288 | 99.65 | 99.65 | 97.26 | 5.53 |
27
+ | HOST | 2416 | 80.55 | 94.82 | 86.80 | 5.37 |
28
+ | WOST | 2416 | 89.98 | 97.16 | 91.79 | 5.39 |
29
+ |-----------|-----------|----------|---------|------------|--------------|
30
+ | Combined | 14315 | 92.39 | 97.84 | 93.68 | 5.35 |
31
+
32
+
33
+ New set:
34
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
35
+ |:--------:|----------:|---------:|--------:|-----------:|-------------:|
36
+ | ArT | 35149 | 86.24 | 95.52 | 92.95 | 5.41 |
37
+ | COCOv1.4 | 9825 | 82.47 | 94.29 | 87.33 | 5.91 |
38
+ | Uber | 80551 | 91.19 | 96.40 | 91.74 | 5.36 |
39
+ |----------|-----------|----------|---------|------------|--------------|
40
+ | Combined | 125525 | 89.12 | 95.99 | 91.73 | 5.42 |
41
+
42
+
43
+ Time: Total 4061.6468493938446s, Average 29.044957447038364ms. Total samples 139840.
clip4str_large_3c9d881b88.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d1638c057c6cd827c7a048715179f1a7af6a678ae2c9c75ee7fd72b1a1eccc
3
+ size 1787639049
clip4str_large_3c9d881b88_log.txt ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Benchmark (Subset) set:
2
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
3
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
4
+ | IIIT5k | 3000 | 99.60 | 99.88 | 97.77 | 5.09 |
5
+ | SVT | 647 | 98.61 | 99.63 | 97.18 | 5.87 |
6
+ | IC13_1015 | 1015 | 99.01 | 99.63 | 97.73 | 5.32 |
7
+ | IC15_1811 | 1811 | 91.88 | 97.52 | 94.77 | 5.37 |
8
+ | IC15_2077 | 2077 | 91.43 | 97.33 | 94.19 | 5.33 |
9
+ | SVTP | 645 | 98.14 | 99.44 | 96.42 | 5.86 |
10
+ | CUTE80 | 288 | 99.65 | 99.94 | 97.37 | 5.54 |
11
+ | HOST | 2416 | 81.08 | 94.91 | 88.33 | 5.38 |
12
+ | WOST | 2416 | 90.60 | 97.26 | 93.04 | 5.39 |
13
+ |-----------|-----------|----------|---------|------------|--------------|
14
+ | Combined | 14315 | 92.64 | 97.88 | 94.38 | 5.35 |
15
+
16
+
17
+ Benchmark set:
18
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
19
+ |:---------:|----------:|---------:|--------:|-----------:|-------------:|
20
+ | IIIT5k | 3000 | 99.60 | 99.88 | 97.77 | 5.09 |
21
+ | SVT | 647 | 98.61 | 99.63 | 97.18 | 5.87 |
22
+ | IC13_1015 | 1015 | 99.01 | 99.63 | 97.73 | 5.32 |
23
+ | IC15_1811 | 1811 | 91.88 | 97.52 | 94.77 | 5.37 |
24
+ | IC15_2077 | 2077 | 91.43 | 97.33 | 94.19 | 5.33 |
25
+ | SVTP | 645 | 98.14 | 99.44 | 96.42 | 5.86 |
26
+ | CUTE80 | 288 | 99.65 | 99.94 | 97.37 | 5.54 |
27
+ | HOST | 2416 | 81.08 | 94.91 | 88.33 | 5.38 |
28
+ | WOST | 2416 | 90.60 | 97.26 | 93.04 | 5.39 |
29
+ |-----------|-----------|----------|---------|------------|--------------|
30
+ | Combined | 14315 | 92.64 | 97.88 | 94.38 | 5.35 |
31
+
32
+
33
+ New set:
34
+ | Dataset | # samples | Accuracy | 1 - NED | Confidence | Label Length |
35
+ |:--------:|----------:|---------:|--------:|-----------:|-------------:|
36
+ | ArT | 35149 | 86.43 | 95.62 | 93.62 | 5.41 |
37
+ | COCOv1.4 | 9825 | 82.68 | 94.43 | 88.30 | 5.92 |
38
+ | Uber | 80551 | 92.20 | 96.79 | 92.85 | 5.37 |
39
+ |----------|-----------|----------|---------|------------|--------------|
40
+ | Combined | 125525 | 89.84 | 96.28 | 92.71 | 5.42 |
41
+
42
+
43
+ Time: Total 2185.2176456451416s, Average 15.626556390482992ms. Total samples 139840.