source code

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+.idea/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# custom
+*.pkl
+*.log
+outputs/
+.log/
+.tb_log/
+data_log/
+datasets/
+#*zip

.gitmodules

+[submodule "third_party/zed-ros-wrapper"]
+	path = third_party/zed-ros-wrapper
+	url = https://github.com/stereolabs/zed-ros-wrapper.git
+[submodule "third_party/kinova-ros"]
+	path = third_party/kinova-ros
+	url = git@github.com:ckorbach/kinova-ros.git

README.md

-# next_best_view_rl_benchmark
+# next_best_view_rl
+This project is an extension to work presented in this [repository](https://gitlab.uni-koblenz.de/ckorbach/next_best_view_rl). The project aims to find the sequence of next-best-views of occluded and self-occluded objects using reinforcement learning algorithms: PPO, SAC, TD3, and A2C. We trained each algorithm separately on three different datasets, extracted from [TEOS dataset](https://data.nvision.eecs.yorku.ca/TEOS/), for five runs using random seed. We compared the performance of the algorithms during training and evaluation. We could find that SAC outperforms all the other algorithms.
+# Setup
+
+1. Clone the repository: `git clone --recurse-submodules ...`
+2. in 'third_party/zed-ros-wrapper' verify branch `devel`: `git checkout devel`
+3. `sudo apt-get update && sudo apt-get install cmake libopenmpi-dev python3-dev zlib1g-dev libosmesa6-dev libgl1-mesa-glx libglfw3'
+4. Create virtual environment: `conda create --name nbv_env python=3.7`
+5. Activate virual environment: 'conda activate nbv_env'
+6. Download and unpack mjpro150 ([link](https://roboti.us/download.html)) and move the `mjpro150` folder into `~/.mujoco/`
+7. Download and copy a license key ([link](https://roboti.us/license.htmlo)) into `~/.mujoco/`
+8. Add `LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/USER/.mujoco/mjpro150/bin` to your `.bashrc`
+9. Install mujoco from `https://github.com/openai/mujoco-py`
+10. Install requirements: `pip install -r requirements.txt`
+11. Install setup.py: `pip install -e .`
+
+# Execution
+
+- modify configs in `config` with hydra framework
+- to execute training of ppo algorithm
+	- start RL training: `python3 scripts/train.py algorithm=ppo`
+	- evaluate RL model: `python3 scripts/evaluate.py algorithm=ppo`
 
-
-
-## Getting started
-
-To make it easy for you to get started with GitLab, here's a list of recommended next steps.
-
-Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
-
-## Add your files
-
-- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
-- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
-
-```
-cd existing_repo
-git remote add origin https://gitlab.uni-koblenz.de/nbeili/next_best_view_rl_benchmark.git
-git branch -M main
-git push -uf origin main
-```
-
-## Integrate with your tools
-
-- [ ] [Set up project integrations](https://gitlab.uni-koblenz.de/nbeili/next_best_view_rl_benchmark/-/settings/integrations)
-
-## Collaborate with your team
-
-- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
-- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
-- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
-- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
-- [ ] [Automatically merge when pipeline succeeds](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
-
-## Test and Deploy
-
-Use the built-in continuous integration in GitLab.
-
-- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
-- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing(SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
-- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
-- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
-- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
-
-***
-
-# Editing this README
-
-When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thank you to [makeareadme.com](https://www.makeareadme.com/) for this template.
-
-## Suggestions for a good README
-Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
-
-## Name
-Choose a self-explaining name for your project.
-
-## Description
-Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
-
-## Badges
-On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
-
-## Visuals
-Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
-
-## Installation
-Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
-
-## Usage
-Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
-
-## Support
-Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
-
-## Roadmap
-If you have ideas for releases in the future, it is a good idea to list them in the README.
-
-## Contributing
-State if you are open to contributions and what your requirements are for accepting them.
-
-For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
-
-You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
-
-## Authors and acknowledgment
-Show your appreciation to those who have contributed to the project.
-
-## License
-For open source projects, say how it is licensed.
-
-## Project status
-If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.

classification/basicnet.py

+"""
+SimpleNet in Pytorch
+github.com/Coderx7/SimpleNet_Pytorch
+github.com/Coderx7/TF_Pytorch_testbed/blob/master/Pytorch/models/simplenet.py
+https://heartbeat.fritz.ai/basics-of-image-classification-with-pytorch-2f8973c51864
+"""
+
+import torch.nn as nn
+
+
+class Unit(nn.Module):
+    def __init__(self, in_channels, out_channels):
+        super(Unit, self).__init__()
+
+        self.conv = nn.Conv2d(in_channels=in_channels, kernel_size=3, out_channels=out_channels, stride=1, padding=1)
+        self.bn = nn.BatchNorm2d(num_features=out_channels)
+        self.relu = nn.ReLU()
+
+    def forward(self, input):
+        output = self.conv(input)
+        output = self.bn(output)
+        output = self.relu(output)
+
+        return output
+
+
+class BasicNet(nn.Module):
+    def __init__(self, classes=10):
+        super(BasicNet, self).__init__()
+
+        # Create 14 layers of the unit with max pooling in between
+        self.unit1 = Unit(in_channels=3, out_channels=32)
+        self.unit2 = Unit(in_channels=32, out_channels=32)
+        self.unit3 = Unit(in_channels=32, out_channels=32)
+
+        self.pool1 = nn.MaxPool2d(kernel_size=2)
+
+        self.unit4 = Unit(in_channels=32, out_channels=64)
+        self.unit5 = Unit(in_channels=64, out_channels=64)
+        self.unit6 = Unit(in_channels=64, out_channels=64)
+        self.unit7 = Unit(in_channels=64, out_channels=64)
+
+        self.pool2 = nn.MaxPool2d(kernel_size=2)
+
+        self.unit8 = Unit(in_channels=64, out_channels=128)
+        self.unit9 = Unit(in_channels=128, out_channels=128)
+        self.unit10 = Unit(in_channels=128, out_channels=128)
+        self.unit11 = Unit(in_channels=128, out_channels=128)
+
+        self.pool3 = nn.MaxPool2d(kernel_size=2)
+
+        self.unit12 = Unit(in_channels=128, out_channels=128)
+        self.unit13 = Unit(in_channels=128, out_channels=128)
+        self.unit14 = Unit(in_channels=128, out_channels=128)
+
+        self.avgpool = nn.AvgPool2d(kernel_size=4)
+
+        # Add all the units into the Sequential layer in exact order
+        self.net = nn.Sequential(self.unit1, self.unit2, self.unit3, self.pool1, self.unit4, self.unit5, self.unit6
+                                 , self.unit7, self.pool2, self.unit8, self.unit9, self.unit10, self.unit11, self.pool3,
+                                 self.unit12, self.unit13, self.unit14, self.avgpool)
+
+        self.fc = nn.Linear(in_features=128*7*7, out_features=classes)
+
+    def forward(self, input):
+        output = self.net(input)
+        # print(output.shape)
+        output = output.view(output.size(0), -1)
+        # output = output.view(-1, 128)
+        output = self.fc(output)
+        return output

classification/netloader.py

+import torch
+import torch.nn as nn
+from torchvision import models
+from classification.simplenet import SimpleNet
+from classification.basicnet import BasicNet
+
+
+class NetLoader:
+
+    def __init__(self, model_name, num_classes, resize_size=224,
+                 feature_extract=True, use_pretrained=True, custom_pre_model=None):
+        self.model_name = model_name
+        self.num_classes = num_classes
+        self.resize_size = resize_size
+        self.feature_extract = feature_extract
+        self.use_pretrained = use_pretrained
+        self.custom_pre_model = custom_pre_model
+
+        self.model, self.input_size = self.initialize_model()
+
+    def get_model(self):
+        return self.model, self.input_size
+
+    def initialize_model(self):
+        # Initialize these variables which will be set in this if statement. Each of these
+        #   variables is model specific.
+        model_ft = None
+        input_size = 0
+
+        if self.model_name == "basicnet":
+            """ BasicNet
+            """
+            model_ft = BasicNet(classes=self.num_classes)
+            input_size = self.resize_size
+            # TODO check for None
+            if self.use_pretrained and self.custom_pre_model:
+                checkpoint =torch.load(self.custom_pre_model)
+                model_ft.load_state_dict(checkpoint)
+                model_ft.train()
+
+        elif self.model_name == "simplenet":
+            """ SimpleNet
+            """
+            model_ft = SimpleNet(classes=self.num_classes)
+            input_size = self.resize_size
+            if self.use_pretrained and self.custom_pre_model:
+                checkpoint = torch.load(self.custom_pre_model)
+                model_ft.load_state_dict(checkpoint)
+                model_ft.train()
+
+        elif self.model_name == "resnet18":
+            """ Resnet18
+            """
+            model_ft = models.resnet18(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "resnet34":
+            """ Resnet34
+            """
+            model_ft = models.resnet34(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "resnet50":
+            """ Resnet50
+            """
+            model_ft = models.resnet50(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "resnet101":
+            """ Resnet101
+            """
+            model_ft = models.resnet101(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "resnet152":
+            """ Resnet152
+            """
+            model_ft = models.resnet152(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "alexnet":
+            """ Alexnet
+            """
+            model_ft = models.alexnet(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.classifier[6].in_features
+            model_ft.classifier[6] = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "vgg":
+            """ VGG11_bn
+            """
+            model_ft = models.vgg11_bn(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.classifier[6].in_features
+            model_ft.classifier[6] = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif self.model_name == "squeezenet":
+            """ Squeezenet
+            """
+            model_ft = models.squeezenet1_0(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            model_ft.classifier[1] = nn.Conv2d(512, self.num_classes, kernel_size=(1,1), stride=(1,1))
+            model_ft.num_classes = self.num_classes
+            input_size = 224
+
+        elif self.model_name == "densenet":
+            """ Densenet
+            """
+            model_ft = models.densenet121(pretrained=self.use_pretrained)
+            self.set_parameter_requires_grad(model_ft, self.feature_extract)
+            num_ftrs = model_ft.classifier.in_features
+            model_ft.classifier = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 224
+
+        elif  self.model_name == "inception":
+            """ Inception v3
+            Be careful, expects (299,299) sized images and has auxiliary output
+            """
+            model_ft = models.inception_v3(pretrained= self.use_pretrained, aux_logits=False)
+            self.set_parameter_requires_grad(model_ft,  self.feature_extract)
+            # Handle the auxilary net
+            # num_ftrs = model_ft.AuxLogits.fc.in_features
+            # model_ft.AuxLogits.fc = nn.Linear(num_ftrs,  self.num_classes)
+            # Handle the primary net
+            num_ftrs = model_ft.fc.in_features
+            model_ft.fc = nn.Linear(num_ftrs, self.num_classes)
+            input_size = 299
+
+        else:
+            print("Invalid model name, exiting...")
+            exit()
+
+        return model_ft, input_size
+
+    @staticmethod
+    def set_parameter_requires_grad(model, feature_extracting):
+        if feature_extracting:
+            for param in model.parameters():
+                param.requires_grad = False

classification/predictor.py

+import os
+import numpy as np
+
+import torch
+from torchvision.transforms import transforms
+from torch.autograd import Variable
+from PIL import Image
+import matplotlib.pyplot as plt
+import pandas as pd
+import seaborn as sn
+import torch.nn as nn
+
+from sklearn.manifold import TSNE
+import umap.umap_ as umap
+import umap.plot
+import json
+
+from classification.netloader import NetLoader
+
+
+class Predictor:
+
+    def __init__(self, cfg, test=False):
+        self.cfg = cfg
+        #torch.manuel_seed(self.cfg.classificator.seed)
+        #torch.backends.cudnn.deterministic = True
+        #torch.backends.cudnn.benchmark = False
+        self.print_debug = False
+        self.test = test
+        root_dir = self.cfg.system.project_path
+        if self.test:
+            self.model_dir_path = self.cfg.classificator.test_model_path
+            self.model_path = os.path.join(self.model_dir_path, self.cfg.classificator.test_model)
+            self.class_map_path = os.path.join(self.model_dir_path, self.cfg.classificator.class_map)
+            self.net = self.cfg.classificator.net
+            self.resize_size = self.cfg.classificator.resize_size
+            self.activation = self.cfg.classificator.activation
+        else:
+            self.model_dir_path = root_dir + self.cfg.model.path
+            self.model_path = os.path.join(self.model_dir_path, self.cfg.model.model)
+            self.class_map_path = os.path.join(self.model_dir_path, self.cfg.model.class_map)
+            self.net = self.cfg.model.net
+            self.resize_size = self.cfg.model.resize_size
+            self.activation = self.cfg.model.activation
+        self.model_name = self.model_path.split("/")[-1].split(".")[0]
+        print("[Predictor] Model: %s: " % self.model_path)
+
+        self.class_map = json.load(open(self.class_map_path))
+        self.classes = len(self.class_map.keys())
+
+        netloader = NetLoader(model_name=self.net,
+                              num_classes=self.classes,
+                              resize_size=self.resize_size)
+        self.model, self.resize = netloader.get_model()
+        self.softmax = nn.Softmax(dim=1)
+        self.sigmoid = nn.Sigmoid()
+
+        self.cuda_avail = torch.cuda.is_available()
+        if self.cuda_avail:
+            self.model = self.model.cuda()
+
+        checkpoint = torch.load(self.model_path)
+        self.model.load_state_dict(checkpoint)
+        self.model.eval()
+
+
+    def predict_image(self, image, resize=224, use_activation=True):
+        if isinstance(image, str):
+            image = Image.open(image)
+            image = Image.fromarray(np.uint8(image)).convert("RGB")
+        elif isinstance(image, np.ndarray):
+            image = Image.fromarray(np.uint8(image)).convert("RGB")
+
+        # Define transformations for the image, should
+        transformation = transforms.Compose([
+            transforms.Resize(resize),
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+        ])
+
+        # Pre-process the image
+        image_tensor = transformation(image).float()
+
+        # Add an extra batch dimension since pytorch treats all images as batches
+        image_tensor = image_tensor.unsqueeze_(0)
+        if self.cuda_avail:
+            image_tensor.cuda()
+            dtype = torch.cuda.FloatTensor
+            input = torch.autograd.Variable(image_tensor.type(dtype))
+        else:
+            # Turn the input into a Variable
+            input = Variable(image_tensor)
+
+        # Predict the class of the image
+        output = self.model(input)
+        if use_activation:
+            if self.activation == "softmax":
+                output = self.softmax(output)
+            elif self.activation == "sigmoid":
+                output = self.sigmoid(output)
+            elif self.activation is None:
+                pass
+            else:
+                print("[Error] self.activation wrong defined, using None")
+
+        # print(output)
+        output_data = output.data.cpu().numpy()
+
+        if self.print_debug:
+            print(f"{output}: {output}")
+        return output_data[0]
+
+
+    def get_predicted_object(self, output_data):
+        index = output_data.argmax()
+        accuracy = output_data[index]
+        acc_rounded = float(str(round(accuracy)))