Mask-RCNN-master.zip，Mask-RCNN安装文件

资源文件列表(大概)

文件名

大小

Mask_RCNN-master/

Mask_RCNN-master/.gitignore

569B

Mask_RCNN-master/LICENSE

1.07KB

Mask_RCNN-master/MANIFEST.in

58B

Mask_RCNN-master/README.md

13.44KB

Mask_RCNN-master/assets/

Mask_RCNN-master/assets/4k_video.gif

11.61MB

Mask_RCNN-master/assets/balloon_color_splash.gif

9.21MB

Mask_RCNN-master/assets/detection_activations.png

69.11KB

Mask_RCNN-master/assets/detection_anchors.png

746.79KB

Mask_RCNN-master/assets/detection_final.png

887.11KB

Mask_RCNN-master/assets/detection_histograms.png

13.43KB

Mask_RCNN-master/assets/detection_masks.png

9.75KB

Mask_RCNN-master/assets/detection_refinement.png

702.75KB

Mask_RCNN-master/assets/detection_tensorboard.png

43.08KB

Mask_RCNN-master/assets/images_to_osm.png

983.02KB

Mask_RCNN-master/assets/mapping_challenge.png

613.2KB

Mask_RCNN-master/assets/nucleus_segmentation.png

708.45KB

Mask_RCNN-master/assets/project_3dbuildings.png

959.02KB

Mask_RCNN-master/assets/project_grass_gis.png

578.81KB

Mask_RCNN-master/assets/project_ice_wedge_polygons.png

1MB

Mask_RCNN-master/assets/project_shiny1.jpg

216.48KB

Mask_RCNN-master/assets/project_usiigaci1.gif

2.54MB

Mask_RCNN-master/assets/project_usiigaci2.gif

609.42KB

Mask_RCNN-master/assets/street.png

890.48KB

Mask_RCNN-master/images/

Mask_RCNN-master/images/1045023827_4ec3e8ba5c_z.jpg

137.64KB

Mask_RCNN-master/images/12283150_12d37e6389_z.jpg

66.75KB

Mask_RCNN-master/images/2383514521_1fc8d7b0de_z.jpg

203.23KB

Mask_RCNN-master/images/2502287818_41e4b0c4fb_z.jpg

130.58KB

Mask_RCNN-master/images/2516944023_d00345997d_z.jpg

176.98KB

Mask_RCNN-master/images/25691390_f9944f61b5_z.jpg

176.2KB

Mask_RCNN-master/images/262985539_1709e54576_z.jpg

121.88KB

Mask_RCNN-master/images/3132016470_c27baa00e8_z.jpg

169.62KB

Mask_RCNN-master/images/3627527276_6fe8cd9bfe_z.jpg

157.16KB

Mask_RCNN-master/images/3651581213_f81963d1dd_z.jpg

147.02KB

Mask_RCNN-master/images/3800883468_12af3c0b50_z.jpg

119.68KB

Mask_RCNN-master/images/3862500489_6fd195d183_z.jpg

94.01KB

Mask_RCNN-master/images/3878153025_8fde829928_z.jpg

85.81KB

Mask_RCNN-master/images/4410436637_7b0ca36ee7_z.jpg

123.79KB

Mask_RCNN-master/images/4782628554_668bc31826_z.jpg

223.71KB

Mask_RCNN-master/images/5951960966_d4e1cda5d0_z.jpg

157.21KB

Mask_RCNN-master/images/6584515005_fce9cec486_z.jpg

142.24KB

Mask_RCNN-master/images/6821351586_59aa0dc110_z.jpg

212.46KB

Mask_RCNN-master/images/7581246086_cf7bbb7255_z.jpg

142.37KB

Mask_RCNN-master/images/7933423348_c30bd9bd4e_z.jpg

208.56KB

Mask_RCNN-master/images/8053677163_d4c8f416be_z.jpg

219.62KB

Mask_RCNN-master/images/8239308689_efa6c11b08_z.jpg

221.09KB

Mask_RCNN-master/images/8433365521_9252889f9a_z.jpg

177.85KB

Mask_RCNN-master/images/8512296263_5fc5458e20_z.jpg

145.92KB

Mask_RCNN-master/images/8699757338_c3941051b6_z.jpg

234.31KB

Mask_RCNN-master/images/8734543718_37f6b8bd45_z.jpg

162.83KB

Mask_RCNN-master/images/8829708882_48f263491e_z.jpg

237.28KB

Mask_RCNN-master/images/9118579087_f9ffa19e63_z.jpg

300.74KB

Mask_RCNN-master/images/9247489789_132c0d534a_z.jpg

282.17KB

Mask_RCNN-master/mrcnn/

Mask_RCNN-master/mrcnn/__init__.py

Mask_RCNN-master/mrcnn/config.py

9.44KB

Mask_RCNN-master/mrcnn/model.py

123.84KB

Mask_RCNN-master/mrcnn/parallel_model.py

6.92KB

Mask_RCNN-master/mrcnn/utils.py

33.47KB

Mask_RCNN-master/mrcnn/visualize.py

18.51KB

Mask_RCNN-master/requirements.txt

106B

Mask_RCNN-master/samples/

Mask_RCNN-master/samples/balloon/

Mask_RCNN-master/samples/balloon/README.md

1.94KB

Mask_RCNN-master/samples/balloon/balloon.py

13.71KB

Mask_RCNN-master/samples/balloon/inspect_balloon_data.ipynb

7.8MB

Mask_RCNN-master/samples/balloon/inspect_balloon_model.ipynb

9.99MB

Mask_RCNN-master/samples/coco/

Mask_RCNN-master/samples/coco/coco.py

21.04KB

Mask_RCNN-master/samples/coco/inspect_data.ipynb

7.84MB

Mask_RCNN-master/samples/coco/inspect_model.ipynb

9.84MB

Mask_RCNN-master/samples/coco/inspect_weights.ipynb

1.21MB

Mask_RCNN-master/samples/demo.ipynb

1.48MB

Mask_RCNN-master/samples/nucleus/

Mask_RCNN-master/samples/nucleus/README.md

1.25KB

Mask_RCNN-master/samples/nucleus/inspect_nucleus_data.ipynb

4.21MB

Mask_RCNN-master/samples/nucleus/inspect_nucleus_model.ipynb

6.59MB

Mask_RCNN-master/samples/nucleus/nucleus.py

18.05KB

Mask_RCNN-master/samples/shapes/

Mask_RCNN-master/samples/shapes/shapes.py

7.41KB

Mask_RCNN-master/samples/shapes/train_shapes.ipynb

99.23KB

Mask_RCNN-master/setup.cfg

99B

Mask_RCNN-master/setup.py

2.46KB

资源内容介绍

安装可以查看，含一些报错解决方案，https://mp.csdn.net/mp_blog/creation/editor/140853795Mask 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 SegmentationThis 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 datasetThe 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 stepsto 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 DetectionTo 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 filteringVisualizes 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 RefinementThis 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 GenerationExamples of generated masks. These then get scaled and placed on the image in the right location.![](assets/detection_masks.png)## 4.Layer activationsOften 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 HistogramsAnother 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 TensorBoardTensorBoard 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 COCOWe're providing pre-trained weights for MS COCO to make it easier to start. You canuse 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 thismodule in Jupyter notebook (see the provided notebooks for examples) or youcan run it directly from the command line as such:```# Train a new model starting from pre-trained COCO weightspython3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=coco# Train a new model starting from ImageNet weightspython3 samples/coco/coco.py train --dataset=/path/to/coco/ --model=imagenet# Continue training a model that you had trained earlierpython3 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 modelpython3 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 DatasetStart 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 thesame 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 PaperThis 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 betoo high, and often causes the weights to explode, especially when using a small batchsize. It might be related to differences between how Caffe and TensorFlow compute gradients (sum vs

用户评论 (0)

发表评论

您的昵称:

评分

评论内容:

验证码:

Mask-RCNN-master.zip，Mask-RCNN安装文件

资源文件列表(大概)

资源内容介绍

用户评论 (0)

发表评论

相关资源

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

达梦数据库连接驱动-jdbc-20240326.zip

2022csp.zip

NAT类型测试工具（NatTypeTester）