How can I load coco keypoints dataset (image and keypoint annotations) in tensorflow using tf.data.Dataset?
There's a coco Dataset in tensorflow but it's only for object detection.
Regards.
Related
I want to train YOLOv3 Darknet on a custom dataset using MS COCO pre-trained weights. Specifically, i want to fine-tune the MS COCO pre-trained weights of the YOLOv3 on a custom dataset.
I followed the instructions of data preparation and detector configuration in the AlexeyAB/darknet Github repository, but in pre-trained weights part, only the use of ImageNet pre-trained convolutional weights was explained. I googled about fine-tuning MS COCO pre-trained weights of the YOLOv3 on a custom dataset, but couldn't found any explanation.
I trained yolov5 on custom dataset having coco annotation file and got prediction.json file. My question is how I can get coco metric using custom dataset.
Is it possible to use CenterNet with MobilenetV2 backbone (TF Lite compatible) to perform keypoints detection on a custom dataset? Is there a tutorial somewhere?
I have something for training keypoint detection model for custom dataset on Centernet model with hourglass backbone.
This github repo Custom Keypoint Detection for dataset preparation, model training and inference on Centernet-hourglass104 keypoint detection model based on Tensorflow Object detection API with examples.
This could help you in training your keypoint detection model on custom dataset.
Any issues related to the project can be raised in the github itself and doubts can be cleared here.
I am trying to use the Inception SSD model in tensorflow object detection API. To initialize the weights i want to use pretrained Inception V2 On image net as the feature extractor. I see the model config file lets you use a pretrained model on COCO but if I want to use an Image net model how should I go about it?
To train on Imagenet classification models, do the following:
1) Download a pre-trained model from the "Pre-trained models" section on the Slim page
2) Point the fine_tune_checkpoint at that directory
3) Set from_detection_checkpoint to be false (as you will now be fine-tuning from a classification checkpoint)
Note that training from an Imagenet classification checkpoint will require significantly more time.
In TensorFlow's Object Detection API:
https://github.com/tensorflow/models/tree/master/object_detection
Is it possible to classify using the ImageNet classes (1000 classes)? The 4-5 models in the Model Zoo are all trained on the COCO dataset, which only has 80 classes.
Yes, you can convert imagenet data to torecord, and train imagenet detection model, it is the same with coco or pascal_voc procedure.
Here I write a script tensorflow_object_detection_create_coco_tfrecord to convert coco data to tfrecord for tensorflow object detection API, you can refer to this to convert your own data