首页下载资源后端Mask-RCNN-master.zip，Mask-RCNN安装文件

ZIPMask-RCNN-master.zip，Mask-RCNN安装文件

qq_6152355173.68MB需要积分:1

资源文件列表:

Mask_RCNN-master.zip 大约有85个文件
  1. Mask_RCNN-master/
  2. Mask_RCNN-master/.gitignore 569B
  3. Mask_RCNN-master/LICENSE 1.07KB
  4. Mask_RCNN-master/MANIFEST.in 58B
  5. Mask_RCNN-master/README.md 13.44KB
  6. Mask_RCNN-master/assets/
  7. Mask_RCNN-master/assets/4k_video.gif 11.61MB
  8. Mask_RCNN-master/assets/balloon_color_splash.gif 9.21MB
  9. Mask_RCNN-master/assets/detection_activations.png 69.11KB
  10. Mask_RCNN-master/assets/detection_anchors.png 746.79KB
  11. Mask_RCNN-master/assets/detection_final.png 887.11KB
  12. Mask_RCNN-master/assets/detection_histograms.png 13.43KB
  13. Mask_RCNN-master/assets/detection_masks.png 9.75KB
  14. Mask_RCNN-master/assets/detection_refinement.png 702.75KB
  15. Mask_RCNN-master/assets/detection_tensorboard.png 43.08KB
  16. Mask_RCNN-master/assets/images_to_osm.png 983.02KB
  17. Mask_RCNN-master/assets/mapping_challenge.png 613.2KB
  18. Mask_RCNN-master/assets/nucleus_segmentation.png 708.45KB
  19. Mask_RCNN-master/assets/project_3dbuildings.png 959.02KB
  20. Mask_RCNN-master/assets/project_grass_gis.png 578.81KB
  21. Mask_RCNN-master/assets/project_ice_wedge_polygons.png 1MB
  22. Mask_RCNN-master/assets/project_shiny1.jpg 216.48KB
  23. Mask_RCNN-master/assets/project_usiigaci1.gif 2.54MB
  24. Mask_RCNN-master/assets/project_usiigaci2.gif 609.42KB
  25. Mask_RCNN-master/assets/street.png 890.48KB
  26. Mask_RCNN-master/images/
  27. Mask_RCNN-master/images/1045023827_4ec3e8ba5c_z.jpg 137.64KB
  28. Mask_RCNN-master/images/12283150_12d37e6389_z.jpg 66.75KB
  29. Mask_RCNN-master/images/2383514521_1fc8d7b0de_z.jpg 203.23KB
  30. Mask_RCNN-master/images/2502287818_41e4b0c4fb_z.jpg 130.58KB
  31. Mask_RCNN-master/images/2516944023_d00345997d_z.jpg 176.98KB
  32. Mask_RCNN-master/images/25691390_f9944f61b5_z.jpg 176.2KB
  33. Mask_RCNN-master/images/262985539_1709e54576_z.jpg 121.88KB
  34. Mask_RCNN-master/images/3132016470_c27baa00e8_z.jpg 169.62KB
  35. Mask_RCNN-master/images/3627527276_6fe8cd9bfe_z.jpg 157.16KB
  36. Mask_RCNN-master/images/3651581213_f81963d1dd_z.jpg 147.02KB
  37. Mask_RCNN-master/images/3800883468_12af3c0b50_z.jpg 119.68KB
  38. Mask_RCNN-master/images/3862500489_6fd195d183_z.jpg 94.01KB
  39. Mask_RCNN-master/images/3878153025_8fde829928_z.jpg 85.81KB
  40. Mask_RCNN-master/images/4410436637_7b0ca36ee7_z.jpg 123.79KB
  41. Mask_RCNN-master/images/4782628554_668bc31826_z.jpg 223.71KB
  42. Mask_RCNN-master/images/5951960966_d4e1cda5d0_z.jpg 157.21KB
  43. Mask_RCNN-master/images/6584515005_fce9cec486_z.jpg 142.24KB
  44. Mask_RCNN-master/images/6821351586_59aa0dc110_z.jpg 212.46KB
  45. Mask_RCNN-master/images/7581246086_cf7bbb7255_z.jpg 142.37KB
  46. Mask_RCNN-master/images/7933423348_c30bd9bd4e_z.jpg 208.56KB
  47. Mask_RCNN-master/images/8053677163_d4c8f416be_z.jpg 219.62KB
  48. Mask_RCNN-master/images/8239308689_efa6c11b08_z.jpg 221.09KB
  49. Mask_RCNN-master/images/8433365521_9252889f9a_z.jpg 177.85KB
  50. Mask_RCNN-master/images/8512296263_5fc5458e20_z.jpg 145.92KB
  51. Mask_RCNN-master/images/8699757338_c3941051b6_z.jpg 234.31KB
  52. Mask_RCNN-master/images/8734543718_37f6b8bd45_z.jpg 162.83KB
  53. Mask_RCNN-master/images/8829708882_48f263491e_z.jpg 237.28KB
  54. Mask_RCNN-master/images/9118579087_f9ffa19e63_z.jpg 300.74KB
  55. Mask_RCNN-master/images/9247489789_132c0d534a_z.jpg 282.17KB
  56. Mask_RCNN-master/mrcnn/
  57. Mask_RCNN-master/mrcnn/__init__.py 1B
  58. Mask_RCNN-master/mrcnn/config.py 9.44KB
  59. Mask_RCNN-master/mrcnn/model.py 123.84KB
  60. Mask_RCNN-master/mrcnn/parallel_model.py 6.92KB
  61. Mask_RCNN-master/mrcnn/utils.py 33.47KB
  62. Mask_RCNN-master/mrcnn/visualize.py 18.51KB
  63. Mask_RCNN-master/requirements.txt 106B
  64. Mask_RCNN-master/samples/
  65. Mask_RCNN-master/samples/balloon/
  66. Mask_RCNN-master/samples/balloon/README.md 1.94KB
  67. Mask_RCNN-master/samples/balloon/balloon.py 13.71KB
  68. Mask_RCNN-master/samples/balloon/inspect_balloon_data.ipynb 7.8MB
  69. Mask_RCNN-master/samples/balloon/inspect_balloon_model.ipynb 9.99MB
  70. Mask_RCNN-master/samples/coco/
  71. Mask_RCNN-master/samples/coco/coco.py 21.04KB
  72. Mask_RCNN-master/samples/coco/inspect_data.ipynb 7.84MB
  73. Mask_RCNN-master/samples/coco/inspect_model.ipynb 9.84MB
  74. Mask_RCNN-master/samples/coco/inspect_weights.ipynb 1.21MB
  75. Mask_RCNN-master/samples/demo.ipynb 1.48MB
  76. Mask_RCNN-master/samples/nucleus/
  77. Mask_RCNN-master/samples/nucleus/README.md 1.25KB
  78. Mask_RCNN-master/samples/nucleus/inspect_nucleus_data.ipynb 4.21MB
  79. Mask_RCNN-master/samples/nucleus/inspect_nucleus_model.ipynb 6.59MB
  80. Mask_RCNN-master/samples/nucleus/nucleus.py 18.05KB
  81. Mask_RCNN-master/samples/shapes/
  82. Mask_RCNN-master/samples/shapes/shapes.py 7.41KB
  83. Mask_RCNN-master/samples/shapes/train_shapes.ipynb 99.23KB
  84. Mask_RCNN-master/setup.cfg 99B
  85. Mask_RCNN-master/setup.py 2.46KB

资源介绍:

安装可以查看，含一些报错解决方案，https://mp.csdn.net/mp_blog/creation/editor/140853795 Mask R-CNN（Mask Region-Based Convolutional Neural Network）是一种用于实例分割（Instance Segmentation）的深度学习模型。它是在 Faster R-CNN 的基础上扩展而来，可以同时进行对象检测（Object Detection）、目标实例分割以及对象的语义分割。 让我用更简单的术语解释一下 Mask R-CNN 的工作原理： 1. **对象检测（Object Detection）**：Mask R-CNN 可以识别图像中的不同物体，并确定它们的位置。这类似于在图像中画边界框来标记物体的位置，即确定物体在图像中的位置和大小。 2. **实例分割（Instance Segmentation）**：与对象检测不同，实例分割不仅可以检测物体的位置，还可以为每个检测到的物体生成一个像素级的掩模（mask），将其与图像中其他物体进行区分，从而精确地确定物体边界。 3. *
# Mask R-CNN for Object Detection and Segmentation This is an implementation of [Mask R-CNN](https://arxiv.org/abs/1703.06870) on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone. ![Instance Segmentation Sample](assets/street.png) The repository includes: * Source code of Mask R-CNN built on FPN and ResNet101. * Training code for MS COCO * Pre-trained weights for MS COCO * Jupyter notebooks to visualize the detection pipeline at every step * ParallelModel class for multi-GPU training * Evaluation on MS COCO metrics (AP) * Example of training on your own dataset The code is documented and designed to be easy to extend. If you use it in your research, please consider citing this repository (bibtex below). If you work on 3D vision, you might find our recently released [Matterport3D](https://matterport.com/blog/2017/09/20/announcing-matterport3d-research-dataset/) dataset useful as well. This dataset was created from 3D-reconstructed spaces captured by our customers who agreed to make them publicly available for academic use. You can see more examples [here](https://matterport.com/gallery/). # Getting Started * [demo.ipynb](samples/demo.ipynb) Is the easiest way to start. It shows an example of using a model pre-trained on MS COCO to segment objects in your own images. It includes code to run object detection and instance segmentation on arbitrary images. * [train_shapes.ipynb](samples/shapes/train_shapes.ipynb) shows how to train Mask R-CNN on your own dataset. This notebook introduces a toy dataset (Shapes) to demonstrate training on a new dataset. * ([model.py](mrcnn/model.py), [utils.py](mrcnn/utils.py), [config.py](mrcnn/config.py)): These files contain the main Mask RCNN implementation. * [inspect_data.ipynb](samples/coco/inspect_data.ipynb). This notebook visualizes the different pre-processing steps to prepare the training data. * [inspect_model.ipynb](samples/coco/inspect_model.ipynb) This notebook goes in depth into the steps performed to detect and segment objects. It provides visualizations of every step of the pipeline. * [inspect_weights.ipynb](samples/coco/inspect_weights.ipynb) This notebooks inspects the weights of a trained model and looks for anomalies and odd patterns. # Step by Step Detection To help with debugging and understanding the model, there are 3 notebooks ([inspect_data.ipynb](samples/coco/inspect_data.ipynb), [inspect_model.ipynb](samples/coco/inspect_model.ipynb), [inspect_weights.ipynb](samples/coco/inspect_weights.ipynb)) that provide a lot of visualizations and allow running the model step by step to inspect the output at each point. Here are a few examples: ## 1. Anchor sorting and filtering Visualizes every step of the first stage Region Proposal Network and displays positive and negative anchors along with anchor box refinement. ![](assets/detection_anchors.png) ## 2. Bounding Box Refinement This is an example of final detection boxes (dotted lines) and the refinement applied to them (solid lines) in the second stage. ![](assets/detection_refinement.png) ## 3. Mask Generation Examples of generated masks. These then get scaled and placed on the image in the right location. ![](assets/detection_masks.png) ## 4.Layer activations Often it's useful to inspect the activations at different layers to look for signs of trouble (all zeros or random noise). ![](assets/detection_activations.png) ## 5. Weight Histograms Another useful debugging tool is to inspect the weight histograms. These are included in the inspect_weights.ipynb notebook. ![](assets/detection_histograms.png) ## 6. Logging to TensorBoard TensorBoard is another great debugging and visualization tool. The model is configured to log losses and save weights at the end of every epoch. ![](assets/detection_tensorboard.png) ## 6. Composing the different pieces into a final result ![](assets/detection_final.png) # Training on MS COCO We're providing pre-trained weights for MS COCO to make it easier to start. You can use those weights as a starting point to train your own variation on the network. Training and evaluation code is in `samples/coco/coco.py`. You can import this module in Jupyter notebook (see the provided notebooks for examples) or you can run it directly from the command line as such: ``` # Train a new model starting from pre-trained COCO weights python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=coco # Train a new model starting from ImageNet weights python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=imagenet # Continue training a model that you had trained earlier python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=/path/to/weights.h5 # Continue training the last model you trained. This will find # the last trained weights in the model directory. python3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=last ``` You can also run the COCO evaluation code with: ``` # Run COCO evaluation on the last trained model python3 samples/coco/coco.py evaluate --dataset=/path/to/coco/ --model=last ``` The training schedule, learning rate, and other parameters should be set in `samples/coco/coco.py`. # Training on Your Own Dataset Start by reading this [blog post about the balloon color splash sample](https://engineering.matterport.com/splash-of-color-instance-segmentation-with-mask-r-cnn-and-tensorflow-7c761e238b46). It covers the process starting from annotating images to training to using the results in a sample application. In summary, to train the model on your own dataset you'll need to extend two classes: ```Config``` This class contains the default configuration. Subclass it and modify the attributes you need to change. ```Dataset``` This class provides a consistent way to work with any dataset. It allows you to use new datasets for training without having to change the code of the model. It also supports loading multiple datasets at the same time, which is useful if the objects you want to detect are not all available in one dataset. See examples in `samples/shapes/train_shapes.ipynb`, `samples/coco/coco.py`, `samples/balloon/balloon.py`, and `samples/nucleus/nucleus.py`. ## Differences from the Official Paper This implementation follows the Mask RCNN paper for the most part, but there are a few cases where we deviated in favor of code simplicity and generalization. These are some of the differences we're aware of. If you encounter other differences, please do let us know. * **Image Resizing:** To support training multiple images per batch we resize all images to the same size. For example, 1024x1024px on MS COCO. We preserve the aspect ratio, so if an image is not square we pad it with zeros. In the paper the resizing is done such that the smallest side is 800px and the largest is trimmed at 1000px. * **Bounding Boxes**: Some datasets provide bounding boxes and some provide masks only. To support training on multiple datasets we opted to ignore the bounding boxes that come with the dataset and generate them on the fly instead. We pick the smallest box that encapsulates all the pixels of the mask as the bounding box. This simplifies the implementation and also makes it easy to apply image augmentations that would otherwise be harder to apply to bounding boxes, such as image rotation. To validate this approach, we compared our computed bounding boxes to those provided by the COCO dataset. We found that ~2% of bounding boxes differed by 1px or more, ~0.05% differed by 5px or more, and only 0.01% differed by 10px or more. * **Learning Rate:** The paper uses a learning rate of 0.02, but we found that to be too high, and often causes the weights to explode, especially when using a small batch size. It might be related to differences between how Caffe and TensorFlow compute gradients (sum vs
100+评论
captcha

    相关资源

    1. 步控中文编程软件+视频教学案例+国产PLC控制器+中文编程PLC+中文PLC+步控PLC+中文控制器

      m0_70055387#硬件开发ZIP39.07MB7月前
      资源摘要:中文表格式编程软件，无需使用复杂的编程语言，低代码编程，快速入门，功能模块化。零基础：软件是全中文表格式界面，不需要懂英文代码，完全可以做到零基础使用，像工厂里的电工、装配工都可以直接上手。降成本：软件可以给标准的控制器编写程序，还可以给批量生产的设备定制开发板，大大降低设备成本。无门槛：软件使用底层程序做好的功能模块，直接调用即可，程序单一性，调试修改方便。

    2. 达梦数据库连接驱动-jdbc-20240326.zip

      qq_54065582#数据库ZIP4.81MB7月前
      资源摘要:达梦数据库连接驱动--主要用于kettle native等数据库连接软件的驱动配置

    3. 2022csp.zip

      2401_85583178#行业研究ZIP2.71MB7月前
      资源摘要:2022csp.zip

    4. NAT类型测试工具（NatTypeTester）

      mc_dudu233#网络技术ZIP4.15MB7月前
      资源摘要:NatTypeTester用于帮助用户检测和理解他们的网络连接类型。该项目基于Python语言编写，简单易用，并提供了一种直观的方式来识别你的网络是NAT类型还是直接连接，这对于进行网络诊断、游戏优化或P2P应用开发等场景尤其有价值。NAT类型一般分成下列4种：　　1. Full Cone NAT （彻底圆锥型）　　2. Restricted Cone NAT （详细地址限定圆锥型）　　3. Port Restricted Cone NAT （端口号限定圆锥型）　　4. Symmetric NAT (对称性型)

    5. 各学院调整专业考核方案.zip

      qq_34485651#行业研究ZIP156.08KB7月前
      资源摘要:各学院调整专业考核方案.zip

    6. arcgis for android 10.2.7

      sig321#移动开发ZIP20.86MB7月前
      资源摘要:arcgis for android 10.2.7完整的离线引用的库

    7. GDAL2.2.3 for Android

      sig321#移动开发ZIP24.59MB7月前
      资源摘要:GDAL2.2.3 for Android使用环境： compileSdkVersion 28 buildToolsVersion '28.0.3' defaultConfig { minSdkVersion 23 targetSdkVersion 28 versionCode 3 versionName '3.0' testInstrumentationRunner "android.support.test.runner.AndroidJUnitRunner" multiDexEnabled true }

    8. easyPlayer视频流https://blog.csdn.net/weixin-42120669/article/deta

      weixin_42120669#前端ZIP5.57MB7月前
      资源摘要:vue3直播视频流easy-player easyPlayer视频流 https://blog.csdn.net/weixin_42120669/article/details/140853267
    站长QQ:九六九五七三七