Generally, a higher mAP implies a lower speed, but as this project is based on a one-class object detection problem, the faster model ( SSD MobileNet v2 320x320) should be enough.īesides the Model Zoo, TensorFlow provides a Models Configs Repository as well. This collection is the TensorFlow 2 Detection Model Zoo and can be accessed here.Įvery model has a Speed, Mean Average Precision(mAP) and Output. TensorFlow 2 provides 40 pre-trained detection models on the COCO 2017 Dataset. We’re ready to choose the model that’s going to be the Kangaroo Detector. To do so, transform the data into the TFRecord format using the generate_tf_records.py script available in the Kangaroo Dataset: The last step is to convert the data into a sequence of binary records so that they can be fed into Tensorflow’s object detection API. Kangaroo is the only one, so right-click in the File section on Google Colab and create a New file named labelmap.pbtxt as follows: Now, it’s necessary to create a labelmap file to define the classes that are going to be used. If you want to use it as well, it’s necessary to create a user, go into the account section of Kaggle, and get an API Token: Runtime > Change runtime type > Hardware accelerator: GPUĬlone, install, and test the TensorFlow Object Detection API:Īs mentioned before, the model is going to be trained using the Kangaroo dataset on Kaggle. Setting up the environmentĬreate a new Google Colab notebook and select a GPU as hardware accelerator: If you want to jump straight to the Colab Notebook, click here. The remainder of this section explains how to set up the environment, the model selection, and training. In this project, we’re going to use this API and train the model using a Google Colaboratory Notebook. With a good dataset, it’s time to think about the model.TensorFlow 2 provides an Object Detection API that makes it easy to construct, train, and deploy object detection models. Using LabelImg makes it easy to create your own dataset, but feel free to use my kangaroo dataset, I’ve uploaded it on Kaggle: ymax: Maximum value of the y coordinate of the bounding box.
xmax: Maximum value of the x coordinate of the bounding box.ymin: Minimum bounding box y coordinate value.xmin: Minimum bounding box x coordinate value.To facilitate the conversion to TF.record format (below), I then converted the XML of the program above into two CSV files containing the data already split in train and test (80%-20%). home/hugo/Documents/projects/tfjs/dataset/images/kangaroo-0.jpg It’s going to generate an XML file per image (Pascal VOC format) that contains all annotations and bounding boxes. In that case, I chose just one class, but the software can be used to annotate multiple classes as well.
0 kommentar(er)
