Hugging Face's logo

Spaces:
geopavlakos
/
HaMeR
Build error

App Files Community
4
HaMeR
File size: 4,934 Bytes 
d7a991a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
 
#!/usr/bin/env python
# Copyright (c) OpenMMLab. All rights reserved.
import functools as func
import glob
import re
from os.path import basename, splitext

import numpy as np
import titlecase


def anchor(name):
    return re.sub(r'-+', '-', re.sub(r'[^a-zA-Z0-9]', '-',
                                     name.strip().lower())).strip('-')


# Count algorithms

files = sorted(glob.glob('topics/*.md'))

stats = []

for f in files:
    with open(f, 'r') as content_file:
        content = content_file.read()

    # title
    title = content.split('\n')[0].replace('#', '')

    # count papers
    papers = set(
        (papertype, titlecase.titlecase(paper.lower().strip()))
        for (papertype, paper) in re.findall(
            r'<!--\s*\[([A-Z]*?)\]\s*-->\s*\n.*?\btitle\s*=\s*{(.*?)}',
            content, re.DOTALL))
    # paper links
    revcontent = '\n'.join(list(reversed(content.splitlines())))
    paperlinks = {}
    for _, p in papers:
        print(p)
        paperlinks[p] = ', '.join(
            ((f'[{paperlink} ⇨]'
              f'(topics/{splitext(basename(f))[0]}.html#{anchor(paperlink)})')
             for paperlink in re.findall(
                 rf'\btitle\s*=\s*{{\s*{p}\s*}}.*?\n### (.*?)\s*[,;]?\s*\n',
                 revcontent, re.DOTALL | re.IGNORECASE)))
        print('   ', paperlinks[p])
    paperlist = '\n'.join(
        sorted(f'    - [{t}] {x} ({paperlinks[x]})' for t, x in papers))
    # count configs
    configs = set(x.lower().strip()
                  for x in re.findall(r'.*configs/.*\.py', content))

    # count ckpts
    ckpts = set(x.lower().strip()
                for x in re.findall(r'https://download.*\.pth', content)
                if 'mmpose' in x)

    statsmsg = f"""
## [{title}]({f})

* 模型权重文件数量: {len(ckpts)}
* 配置文件数量: {len(configs)}
* 论文数量: {len(papers)}
{paperlist}

    """

    stats.append((papers, configs, ckpts, statsmsg))

allpapers = func.reduce(lambda a, b: a.union(b), [p for p, _, _, _ in stats])
allconfigs = func.reduce(lambda a, b: a.union(b), [c for _, c, _, _ in stats])
allckpts = func.reduce(lambda a, b: a.union(b), [c for _, _, c, _ in stats])

# Summarize

msglist = '\n'.join(x for _, _, _, x in stats)
papertypes, papercounts = np.unique([t for t, _ in allpapers],
                                    return_counts=True)
countstr = '\n'.join(
    [f'   - {t}: {c}' for t, c in zip(papertypes, papercounts)])

modelzoo = f"""
# 概览

* 模型权重文件数量: {len(allckpts)}
* 配置文件数量: {len(allconfigs)}
* 论文数量: {len(allpapers)}
{countstr}

已支持的数据集详细信息请见 [数据集](datasets.md).

{msglist}

"""

with open('modelzoo.md', 'w') as f:
    f.write(modelzoo)

# Count datasets

files = sorted(glob.glob('tasks/*.md'))
# files = sorted(glob.glob('docs/tasks/*.md'))

datastats = []

for f in files:
    with open(f, 'r') as content_file:
        content = content_file.read()

    # title
    title = content.split('\n')[0].replace('#', '')

    # count papers
    papers = set(
        (papertype, titlecase.titlecase(paper.lower().strip()))
        for (papertype, paper) in re.findall(
            r'<!--\s*\[([A-Z]*?)\]\s*-->\s*\n.*?\btitle\s*=\s*{(.*?)}',
            content, re.DOTALL))
    # paper links
    revcontent = '\n'.join(list(reversed(content.splitlines())))
    paperlinks = {}
    for _, p in papers:
        print(p)
        paperlinks[p] = ', '.join(
            (f'[{p} ⇨](tasks/{splitext(basename(f))[0]}.html#{anchor(p)})'
             for p in re.findall(
                 rf'\btitle\s*=\s*{{\s*{p}\s*}}.*?\n## (.*?)\s*[,;]?\s*\n',
                 revcontent, re.DOTALL | re.IGNORECASE)))
        print('   ', paperlinks[p])
    paperlist = '\n'.join(
        sorted(f'    - [{t}] {x} ({paperlinks[x]})' for t, x in papers))
    # count configs
    configs = set(x.lower().strip()
                  for x in re.findall(r'https.*configs/.*\.py', content))

    # count ckpts
    ckpts = set(x.lower().strip()
                for x in re.findall(r'https://download.*\.pth', content)
                if 'mmpose' in x)

    statsmsg = f"""
## [{title}]({f})

* 论文数量: {len(papers)}
{paperlist}

    """

    datastats.append((papers, configs, ckpts, statsmsg))

alldatapapers = func.reduce(lambda a, b: a.union(b),
                            [p for p, _, _, _ in datastats])

# Summarize

msglist = '\n'.join(x for _, _, _, x in stats)
datamsglist = '\n'.join(x for _, _, _, x in datastats)
papertypes, papercounts = np.unique([t for t, _ in alldatapapers],
                                    return_counts=True)
countstr = '\n'.join(
    [f'   - {t}: {c}' for t, c in zip(papertypes, papercounts)])

modelzoo = f"""
# 概览

* 论文数量: {len(alldatapapers)}
{countstr}

已支持的算法详细信息请见 [模型池](modelzoo.md).

{datamsglist}
"""

with open('datasets.md', 'w') as f:
    f.write(modelzoo)