install.rst 3.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110
  1. Install
  2. ===============================================================
  3. If you encounter any installation issues, please first consult the :doc:`../../additional_notes/faq`.
  4. If the parsing results are not as expected, refer to the :doc:`../../additional_notes/known_issues`.
  5. .. admonition:: Warning
  6. :class: tip
  7. **Pre-installation Notice—Hardware and Software Environment Support**
  8. To ensure the stability and reliability of the project, we only optimize
  9. and test for specific hardware and software environments during
  10. development. This ensures that users deploying and running the project
  11. on recommended system configurations will get the best performance with
  12. the fewest compatibility issues.
  13. By focusing resources on the mainline environment, our team can more
  14. efficiently resolve potential bugs and develop new features.
  15. In non-mainline environments, due to the diversity of hardware and
  16. software configurations, as well as third-party dependency compatibility
  17. issues, we cannot guarantee 100% project availability. Therefore, for
  18. users who wish to use this project in non-recommended environments, we
  19. suggest carefully reading the documentation and FAQ first. Most issues
  20. already have corresponding solutions in the FAQ. We also encourage
  21. community feedback to help us gradually expand support.
  22. .. raw:: html
  23. <style>
  24. table, th, td {
  25. border: 1px solid black;
  26. border-collapse: collapse;
  27. }
  28. </style>
  29. <table>
  30. <tr>
  31. <td colspan="3" rowspan="2">Operating System</td>
  32. </tr>
  33. <tr>
  34. <td>Ubuntu 22.04 LTS</td>
  35. <td>Windows 10 / 11</td>
  36. <td>macOS 11+</td>
  37. </tr>
  38. <tr>
  39. <td colspan="3">CPU</td>
  40. <td>x86_64(unsupported ARM Linux)</td>
  41. <td>x86_64(unsupported ARM Windows)</td>
  42. <td>x86_64 / arm64</td>
  43. </tr>
  44. <tr>
  45. <td colspan="3">Memory</td>
  46. <td colspan="3">16GB or more, recommended 32GB+</td>
  47. </tr>
  48. <tr>
  49. <td colspan="3">Python Version</td>
  50. <td colspan="3">3.10(Please make sure to create a Python 3.10 virtual environment using conda)</td>
  51. </tr>
  52. <tr>
  53. <td colspan="3">Nvidia Driver Version</td>
  54. <td>latest (Proprietary Driver)</td>
  55. <td>latest</td>
  56. <td>None</td>
  57. </tr>
  58. <tr>
  59. <td colspan="3">CUDA Environment</td>
  60. <td>Automatic installation [12.1 (pytorch) + 11.8 (paddle)]</td>
  61. <td>11.8 (manual installation) + cuDNN v8.7.0 (manual installation)</td>
  62. <td>None</td>
  63. </tr>
  64. <tr>
  65. <td rowspan="2">GPU Hardware Support List</td>
  66. <td colspan="2">Minimum Requirement 8G+ VRAM</td>
  67. <td colspan="2">3060ti/3070/4060<br>
  68. 8G VRAM enables layout, formula recognition acceleration and OCR acceleration</td>
  69. <td rowspan="2">None</td>
  70. </tr>
  71. <tr>
  72. <td colspan="2">Recommended Configuration 10G+ VRAM</td>
  73. <td colspan="2">3080/3080ti/3090/3090ti/4070/4070ti/4070tisuper/4080/4090<br>
  74. 10G VRAM or more can enable layout, formula recognition, OCR acceleration and table recognition acceleration simultaneously
  75. </td>
  76. </tr>
  77. </table>
  78. Create an environment
  79. ~~~~~~~~~~~~~~~~~~~~~
  80. .. code-block:: shell
  81. conda create -n MinerU python=3.10
  82. conda activate MinerU
  83. pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com
  84. Download model weight files
  85. ~~~~~~~~~~~~~~~~~~~~~~~~~~
  86. .. code-block:: shell
  87. pip install huggingface_hub
  88. wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
  89. python download_models_hf.py
  90. The MinerU is installed, Check out :doc:`../quick_start` or reading :doc:`boost_with_cuda` for accelerate inference