Tensorflow Lite对象检测csv

jobtbby3  于 2023-09-27  发布在  其他
关注(0)|答案(1)|浏览(107)

我正在使用Tensorflow Lite为Raspberry Pi制作对象检测软件。我已经在运行Tensorflow Lite的情况下正确设置了我的Pi，正确设置了我的Tensorflow Lite模型制作器，并收集和注解了我的图像。现在我只是在努力让这些图像转换成.csv格式，我的模型制作者可以使用。
有没有人有任何提示、教程或建议？
这是我目前的CSV看起来像...

  1. filename,width,height,class,xmin,ymin,xmax,ymax
  2. /content/NameTag (1).jpeg,4032,3024,tag,2120,107,2307,181
  3. /content/NameTag (1).jpeg,4032,3024,tag,2203,1602,2299,1668
  4. /content/NameTag (10).jpeg,4032,3024,tag,2242,220,2368,285
  5. /content/NameTag (10).jpeg,4032,3024,tag,2285,1194,2442,1337
  6. /content/NameTag (10).jpeg,4032,3024,tag,2085,2211,2242,2289
  7. /content/NameTag (100).jpeg,4032,3024,tag,838,2576,1133,2842
  8. /content/NameTag (11).jpeg,4032,3024,tag,2112,2163,2268,2259
  9. /content/NameTag (11).jpeg,4032,3024,tag,2312,1194,2455,1311
  10. /content/NameTag (11).jpeg,4032,3024,tag,2268,211,2385,268
  11. /content/NameTag (12).jpeg,4032,3024,tag,2116,2298,2259,2363
  12. /content/NameTag (12).jpeg,4032,3024,tag,2307,1281,2464,1398
  13. /content/NameTag (12).jpeg,4032,3024,tag,2281,298,2394,359
  14. /content/NameTag (13).jpeg,4032,3024,tag,2790,1968,2933,2050
  15. /content/NameTag (13).jpeg,4032,3024,tag,2985,976,3172,1072
  16. /content/NameTag (13).jpeg,4032,3024,tag,2968,33,3133,124
  17. /content/NameTag (14).jpeg,4032,3024,tag,2107,876,2181,946
  18. /content/NameTag (14).jpeg,4032,3024,tag,2251,1711,2329,1772
  19. /content/NameTag (15).jpeg,4032,3024,tag,2085,1576,2159,1637
  20. /content/NameTag (15).jpeg,4032,3024,tag,2168,1781,2238,1842
  21. /content/NameTag (15).jpeg,4032,3024,tag,2099,833,2190,911
  22. /content/NameTag (16).jpeg,4032,3024,tag,2059,815,2133,885
  23. /content/NameTag (16).jpeg,4032,3024,tag,2068,1620,2155,1689
  24. /content/NameTag (16).jpeg,4032,3024,tag,2094,1820,2185,1889
  25. /content/NameTag (17).jpeg,4032,3024,tag,2125,746,2233,833
  26. /content/NameTag (17).jpeg,4032,3024,tag,2116,1542,2220,1620
  27. /content/NameTag (17).jpeg,4032,3024,tag,2168,1846,2246,1920
  28. /content/NameTag (18).jpeg,4032,3024,tag,2142,624,2242,689
  29. /content/NameTag (18).jpeg,4032,3024,tag,2099,1550,2185,1633
  30. /content/NameTag (18).jpeg,4032,3024,tag,2164,1837,2255,1937
  31. /content/NameTag (19).jpeg,4032,3024,tag,2172,1885,2255,1959
  32. /content/NameTag (19).jpeg,4032,3024,tag,2081,1542,2181,1615
  33. /content/NameTag (19).jpeg,4032,3024,tag,2129,594,2246,668
  34. /content/NameTag (2).jpeg,4032,3024,tag,2464,1794,2533,1872
  35. /content/NameTag (2).jpeg,4032,3024,tag,2107,733,2246,811
  36. /content/NameTag (20).jpeg,4032,3024,tag,3290,1076,3403,1142
  37. /content/NameTag (20).jpeg,4032,3024,tag,3446,1389,3546,1437
  38. /content/NameTag (20).jpeg,4032,3024,tag,3294,1833,3403,1915
  39. /content/NameTag (21).jpeg,4032,3024,tag,3233,963,3338,1020
  40. /content/NameTag (21).jpeg,4032,3024,tag,3442,1263,3538,1320
  41. /content/NameTag (21).jpeg,4032,3024,tag,3272,1868,3381,1937
  42. /content/NameTag (22).jpeg,4032,3024,tag,3207,1976,3316,2055
  43. /content/NameTag (22).jpeg,4032,3024,tag,3425,1302,3516,1359
  44. /content/NameTag (22).jpeg,4032,3024,tag,3120,933,3255,1011
  45. /content/NameTag (23).jpeg,4032,3024,tag,1942,2585,2177,2737
  46. /content/NameTag (23).jpeg,4032,3024,tag,1625,520,1868,685
  47. /content/NameTag (23).jpeg,4032,3024,tag,3046,1163,3194,1298
  48. /content/NameTag (24).jpeg,4032,3024,tag,2225,1146,2307,1233
  49. /content/NameTag (24).jpeg,4032,3024,tag,2277,837,2325,902
  50. /content/NameTag (25).jpeg,4032,3024,tag,2564,2785,2712,2855
  51. /content/NameTag (25).jpeg,4032,3024,tag,1999,1498,2107,1555
  52. /content/NameTag (25).jpeg,4032,3024,tag,2233,646,2338,707
  53. /content/NameTag (26).jpeg,4032,3024,tag,2472,2211,2625,2289
  54. /content/NameTag (26).jpeg,4032,3024,tag,1820,1015,1929,1081
  55. /content/NameTag (26).jpeg,4032,3024,tag,2046,102,2199,211
  56. /content/NameTag (27).jpeg,4032,3024,tag,1755,1520,2033,1707
  57. /content/NameTag (28).jpeg,4032,3024,tag,1694,1550,1964,1720
  58. /content/NameTag (29).jpeg,4032,3024,tag,1585,1550,1894,1720
  59. /content/NameTag (3).jpeg,4032,3024,tag,2203,1037,2307,1133
  60. /content/NameTag (3).jpeg,4032,3024,tag,2481,628,2546,685
  61. /content/NameTag (30).jpeg,4032,3024,tag,1599,1376,1899,1481
  62. /content/NameTag (31).jpeg,4032,3024,tag,2064,1455,2216,1589
  63. /content/NameTag (32).jpeg,4032,3024,tag,2094,1889,2229,1963
  64. /content/NameTag (33).jpeg,4032,3024,tag,2042,1550,2199,1655
  65. /content/NameTag (34).jpeg,4032,3024,tag,712,1542,972,1628
  66. /content/NameTag (34).jpeg,4032,3024,tag,1712,1581,2012,1711
  67. /content/NameTag (35).jpeg,4032,3024,tag,1659,1663,1772,1755
  68. /content/NameTag (36).jpeg,4032,3024,tag,1612,1655,1729,1737
  69. /content/NameTag (37).jpeg,4032,3024,tag,1429,750,1603,872
  70. /content/NameTag (37).jpeg,4032,3024,tag,2381,1528,2442,1594
  71. /content/NameTag (38).jpeg,4032,3024,tag,1964,1215,2042,1281
  72. /content/NameTag (39).jpeg,4032,3024,tag,2433,1398,2533,1455
  73. /content/NameTag (4).jpeg,4032,3024,tag,2381,2268,2516,2333
  74. /content/NameTag (40).jpeg,4032,3024,tag,2081,1628,2259,1737
  75. /content/NameTag (41).jpeg,4032,3024,tag,2046,1489,2229,1611
  76. /content/NameTag (42).jpeg,4032,3024,tag,1272,1555,1577,1715
  77. /content/NameTag (43).jpeg,4032,3024,tag,1877,1320,2099,1468
  78. /content/NameTag (44).jpeg,4032,3024,tag,1972,1563,2181,1681
  79. /content/NameTag (45).jpeg,4032,3024,tag,1564,1342,1925,1533
  80. /content/NameTag (46).jpeg,4032,3024,tag,1916,1489,2142,1655
  81. /content/NameTag (47).jpeg,4032,3024,tag,2085,1615,2242,1676
  82. /content/NameTag (48).jpeg,4032,3024,tag,2799,1776,2925,1920
  83. /content/NameTag (49).jpeg,4032,3024,tag,1746,2176,1933,2272
  84. /content/NameTag (49).jpeg,4032,3024,tag,2159,1350,2290,1463
  85. /content/NameTag (49).jpeg,4032,3024,tag,1912,663,2112,794
  86. /content/NameTag (5).jpeg,4032,3024,tag,2385,2215,2520,2294
  87. /content/NameTag (50).jpeg,4032,3024,tag,1942,733,2020,876
  88. /content/NameTag (50).jpeg,4032,3024,tag,2142,1450,2207,1572
  89. /content/NameTag (51).jpeg,4032,3024,tag,1990,1389,2164,1498
  90. /content/NameTag (51).jpeg,4032,3024,tag,2420,907,2542,972
  91. /content/NameTag (52).jpeg,4032,3024,tag,1872,1055,1981,1120
  92. /content/NameTag (52).jpeg,4032,3024,tag,1899,1372,1999,1442
  93. /content/NameTag (53).jpeg,4032,3024,tag,1855,1642,1968,1724
  94. /content/NameTag (53).jpeg,4032,3024,tag,1872,1320,2007,1394
  95. /content/NameTag (54).jpeg,4032,3024,tag,1833,933,2042,1059
  96. /content/NameTag (55).jpeg,4032,3024,tag,1655,1824,1772,1950
  97. /content/NameTag (56).jpeg,4032,3024,tag,2303,1020,2412,1089
  98. /content/NameTag (57).jpeg,4032,3024,tag,1938,215,2094,311
  99. /content/NameTag (57).jpeg,4032,3024,tag,2238,1046,2346,1111
  100. /content/NameTag (58).jpeg,4032,3024,tag,2081,2011,2155,2089
  101. /content/NameTag (59).jpeg,4032,3024,tag,1751,2050,1933,2172
  102. /content/NameTag (59).jpeg,4032,3024,tag,1059,728,1277,946
  103. /content/NameTag (6).jpeg,3024,4032,tag,776,1575,829,1675
  104. /content/NameTag (6).jpeg,3024,4032,tag,2558,1480,2664,1663
  105. /content/NameTag (60).jpeg,4032,3024,tag,1225,2355,1420,2507
  106. /content/NameTag (61).jpeg,4032,3024,tag,2155,163,2368,333
  107. /content/NameTag (62).jpeg,4032,3024,tag,1538,498,1703,711
  108. /content/NameTag (63).jpeg,4032,3024,tag,1572,168,1703,324
  109. /content/NameTag (64).jpeg,4032,3024,tag,1277,1542,1433,1659
  110. /content/NameTag (65).jpeg,4032,3024,tag,1012,2046,1229,2189
  111. /content/NameTag (65).jpeg,4032,3024,tag,1233,1568,1364,1681
  112. /content/NameTag (66).jpeg,4032,3024,tag,1277,1750,1455,1889
  113. /content/NameTag (67).jpeg,4032,3024,tag,1285,902,1638,989
  114. /content/NameTag (68).jpeg,4032,3024,tag,1516,650,1668,763
  115. /content/NameTag (68).jpeg,4032,3024,tag,1607,1468,1746,1533
  116. /content/NameTag (69).jpeg,4032,3024,tag,1533,463,1720,589
  117. /content/NameTag (69).jpeg,4032,3024,tag,1659,1311,1799,1363
  118. /content/NameTag (69).jpeg,4032,3024,tag,2020,1950,2125,2020
  119. /content/NameTag (7).jpeg,4032,3024,tag,2299,885,2425,946
  120. /content/NameTag (7).jpeg,4032,3024,tag,2368,2724,2499,2820
  121. /content/NameTag (70).jpeg,4032,3024,tag,1603,507,1803,624
  122. /content/NameTag (70).jpeg,4032,3024,tag,1746,1342,1877,1389
  123. /content/NameTag (70).jpeg,4032,3024,tag,1907,1676,2025,1750
  124. /content/NameTag (71).jpeg,4032,3024,tag,1451,1815,1690,1963
  125. /content/NameTag (72).jpeg,4032,3024,tag,2816,472,2894,602
  126. /content/NameTag (72).jpeg,4032,3024,tag,1959,1750,2151,1876
  127. /content/NameTag (73).jpeg,4032,3024,tag,2520,1302,2638,1389
  128. /content/NameTag (73).jpeg,4032,3024,tag,1994,1863,2203,2007
  129. /content/NameTag (74).jpeg,4032,3024,tag,1503,2572,1759,2737
  130. /content/NameTag (74).jpeg,4032,3024,tag,2290,81,2485,268
  131. /content/NameTag (74).jpeg,4032,3024,tag,1677,1024,1916,1194
  132. /content/NameTag (75).jpeg,4032,3024,tag,1285,1468,1612,1907
  133. /content/NameTag (75).jpeg,4032,3024,tag,1120,424,1803,868
  134. /content/NameTag (75).jpeg,4032,3024,tag,2238,2420,2816,2915
  135. /content/NameTag (76).jpeg,4032,3024,tag,877,1,1568,524
  136. /content/NameTag (76).jpeg,4032,3024,tag,2807,1772,3307,2146
  137. /content/NameTag (76).jpeg,4032,3024,tag,1072,2585,1333,3024
  138. /content/NameTag (77).jpeg,4032,3024,tag,672,2289,1416,3024
  139. /content/NameTag (78).jpeg,4032,3024,tag,2581,2302,2768,2755
  140. /content/NameTag (78).jpeg,4032,3024,tag,1890,294,2242,1020
  141. /content/NameTag (79).jpeg,4032,3024,tag,1051,733,2168,2702
  142. /content/NameTag (79).jpeg,4032,3024,tag,2212,555,2525,1820
  143. /content/NameTag (79).jpeg,4032,3024,tag,2529,750,2825,1520
  144. /content/NameTag (8).jpeg,4032,3024,tag,2412,1876,2520,1955
  145. /content/NameTag (80).jpeg,4032,3024,tag,377,1211,1677,2207
  146. /content/NameTag (80).jpeg,4032,3024,tag,1559,915,2377,2150
  147. /content/NameTag (80).jpeg,4032,3024,tag,2351,1002,2968,1589
  148. /content/NameTag (81).jpeg,4032,3024,tag,1638,433,1994,715
  149. /content/NameTag (81).jpeg,4032,3024,tag,2029,1598,2355,1811
  150. /content/NameTag (81).jpeg,4032,3024,tag,1372,2528,1694,2750
  151. /content/NameTag (82).jpeg,4032,3024,tag,2007,450,2416,733
  152. /content/NameTag (82).jpeg,4032,3024,tag,2442,1655,2794,1872
  153. /content/NameTag (82).jpeg,4032,3024,tag,1794,2450,2072,2659
  154. /content/NameTag (83).jpeg,4032,3024,tag,1799,1720,1964,1815
  155. /content/NameTag (84).jpeg,4032,3024,tag,1642,950,1781,1055
  156. /content/NameTag (86).jpeg,4032,3024,tag,2003,1811,2133,1902
  157. /content/NameTag (87).jpeg,4032,3024,tag,1725,1311,1812,1611
  158. /content/NameTag (88).jpeg,4032,3024,tag,512,1763,872,2050
  159. /content/NameTag (89).jpeg,4032,3024,tag,1959,133,2138,411
  160. /content/NameTag (89).jpeg,4032,3024,tag,1538,2189,1820,2655
  161. /content/NameTag (9).jpeg,4032,3024,tag,2259,959,2412,1033
  162. /content/NameTag (90).jpeg,4032,3024,tag,303,328,751,981
  163. /content/NameTag (91).jpeg,4032,3024,tag,2333,1059,2781,1302
  164. /content/NameTag (92).jpeg,4032,3024,tag,1194,2437,1255,2637
  165. /content/NameTag (92).jpeg,4032,3024,tag,2694,1315,2877,1420
  166. /content/NameTag (92).jpeg,4032,3024,tag,1151,524,1238,707
  167. /content/NameTag (93).jpeg,4032,3024,tag,2103,1402,2499,2020
  168. /content/NameTag (94).jpeg,4032,3024,tag,1485,1937,2055,2446
  169. /content/NameTag (95).jpeg,4032,3024,tag,1785,1094,2094,1411
  170. /content/NameTag (95).jpeg,4032,3024,tag,1799,1472,2312,2098
  171. /content/NameTag (96).jpeg,4032,3024,tag,1042,2055,2177,2850
  172. /content/NameTag (97).jpeg,4032,3024,tag,1272,311,1385,485
  173. /content/NameTag (97).jpeg,4032,3024,tag,2581,602,2738,689
  174. /content/NameTag (97).jpeg,4032,3024,tag,1881,2602,2012,2694
  175. /content/NameTag (98).jpeg,4032,3024,tag,1259,2550,1485,2742
  176. /content/NameTag (99).jpeg,4032,3024,tag,1807,389,2103,498

我在Google Colab中运行我的模型制作器，/content/是我的图像所在的位置。
这是我的模型制造商代码

  1. import numpy as np
  2. import os
  4. from tflite_model_maker.config import ExportFormat
  5. from tflite_model_maker import model_spec
  6. from tflite_model_maker import object_detector
  8. import tensorflow as tf
  9. assert tf.__version__.startswith('2')
  11. tf.get_logger().setLevel('ERROR')
  12. from absl import logging
  13. logging.set_verbosity(logging.ERROR)
  15. spec = model_spec.get('efficientdet_lite0')
  17. train_data, validation_data, test_data = object_detector.DataLoader.from_csv('/content/test.csv')
  19. model = object_detector.create(train_data, model_spec=spec, epochs=50, batch_size=8, train_whole_model=True, validation_data=validation_data)

这是我得到的错误

  1. AttributeError                            Traceback (most recent call 
  2.     last)
  3.     <ipython-input-8-cd74bf318e21> in <module>()
  4.           1 
  5.     ----> 2 model = object_detector.create(train_data, model_spec=spec, 
  6.     epochs=50, batch_size=8, train_whole_model=True, 
  7.     validation_data=validation_data)
  9.     /usr/local/lib/python3.7/dist- packages/tensorflow_examples/lite/model_maker/core/task/object_detector.py in create(cls, train_data, model_spec, validation_data, epochs, batch_size, train_whole_model, do_train)
  10.         281           model_spec.compat_tf_versions, compat.get_tf_behavior()))
  11.         282 
  12.     --> 283     object_detector = cls(model_spec, train_data.label_map, 
  13.     train_data)
  14.         284 
  15.         285     if do_train:
  17.     AttributeError: 'NoneType' object has no attribute 'label_map'`
csv

1条答案

按热度按时间
xuo3flqw

xuo3flqw1#

您的CSV格式不正确。
CSV的结构应该是这样的：

  1. TRAINING,a.jpg,NIK,0.03248433451607413,0.03522800346688288,,,0.08648954064904738,0.05116448122571085,,
  2. TRAINING,a.jpg,Name,0.03309341578825052,0.05731540246596025,,,0.060705100126913526,0.06961724494645903,,
  3. TRAINING,b.jpg,NIK,0.03454945054945055,0.03879072581362658,,,0.08973883259597545,0.06085517535899215,,
  4. TRAINING,b.jpg,Name,0.03757813614956471,0.06583747041762307,,,0.05642329099471957,0.0807843555935159,,
  5. TEST,sam_45.jpg,Name,0.0209833413323341,0.03232098987112413,,,0.04926242903560284,0.03803429616147435,,
  6. TEST,sam_46.jpg,NIK,0.019437571862680685,0.02024184021555901,,,0.053739169267411305,0.02787400947716322,,
  7. VALIDATION,sam_47.jpg,NIK,0.03698836813160072,0.013414367060884802,,,0.09344429843772814,0.01615199299167762,,
  8. VALIDATION,sam_47.jpg,NIK,0.03966515793059814,0.06077529566360052,,,0.09466102107363604,0.06378668418747263,,

在第一列中，应该定义TRAINING、TEST或VALIDATION。x和y的值应与图像大小相关，范围介于0和1之间。在x_min, y_min和x_max, y_max之间添加两个空逗号，并在末尾添加。格式应为x_min, y_min,,,x_max, y_max,,，而不是xmin, ymin, xmax, ymax。另外，请记住从CSV中删除标题。

赞(0）分享  回复(0）举报  2023-09-27
我来回答

相关问题

    查看更多

    热门标签

    更多
    JavaquerypythonNode开发语言requestUtil数据库Table后端算法LoggerMessageElementParser

    最新问答

    更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com