Logbook

2018

Weeks 22-25: LSP + MPII datasets

1 minute read

In order to increase the number of samples for future training and evaluation, LSP and MPII datasets have been combined. A script for parsing the labels of b...

Weeks 20-21: Evaluation methodology

3 minute read

Now that we have integrated different CPMs implementations, we must define an evaluation methodology to carry out not just quantitative comparisons as we’ve ...

Weeks 12-13: Tensorflow model (I)

less than 1 minute read

In order to adapt the CPMs TensorFlow version (https://github.com/psycharo/cpm), I’ve been learning TensorFlow basics aided by the tutorials provided in its ...

Back to Top ↑

2017

Weeks 8-11: Influence of image size

1 minute read

In order to get closer to real-time prediction, we’ve been testing how image size influence both execution time and performance. We can experiment with diffe...

Week 7: HumanPose component (v0)

1 minute read

Last week I had troubles matching JdeRobot, Caffe and OpenCV dependencies. Finally, I’ve managed to build a stable environment. I installed JdeRobot from ...

Weeks 5-6: Caffe implementation

1 minute read

These weeks I’ve followed the Jupyter notebook that shows how to use CPMs models trained with Caffe. I’ve divided the workload in two classes: PersonDetector...

Weeks 3-4: Caffe installation

less than 1 minute read

I’ve had troubles trying to install Caffe and its Python bindings. After going through a lot of tutorials, I managed to install it along with Anaconda for Py...

Week 2: CPMs repos

less than 1 minute read

This second week, we’ve tried to reproduce the results obtained in the CPMs paper. Two main approaches have been found: Official release: this repo contai...

Week 1: Literature review

1 minute read

Convolutional Pose Machines (Wei et al.) Convolutional pose machines (CPMs) try to address the human pose estimation problem using convolutional neural netwo...

Back to Top ↑