Comments (5)
So if anyone lands here: this repo is broken. I managed to get it working with the ^^^ above changes plus I had to replace the whole hourglass model. I used this implementation as a reference: https://github.com/yuanyuanli85/Stacked_Hourglass_Network_Keras/blob/eddf0ae15715a88d7859847cfff5f5092b260ae1/src/net/hg_blocks.py . It's implemented in Keras so it's easy to convert to TF2.
from tf2-mobile-2d-single-pose-estimation.
Thank you for answering.
Currently, the master branch is not properly working. I'm trying to solve some trouble by making a tmp
branch. The code of the tmp
branch worked properly, and the conversion to the coreml (or tflite) model is being carried out now.
I will merge the tmp
branch to the master soon.
from tf2-mobile-2d-single-pose-estimation.
I'm seeing very similar broken prediction heatmaps after 70 epochs of training with loss 0.0046
from tf2-mobile-2d-single-pose-estimation.
@tucan9389 I think I found some errors in the code. Here: https://github.com/tucan9389/tf2-mobile-pose-estimation/blob/5248196af945ec81ae1935fd7fbb482e0e3ccf72/hourglass_model.py#L106-L113
Based on my understanding of how the Hourglass network works, it shouldn't merge and average the intermediate heatmaps. Instead, it should just return:
return hg_out, intermediate_heatmap_layers
And later, where you create the model, here: https://github.com/tucan9389/tf2-mobile-pose-estimation/blob/5248196af945ec81ae1935fd7fbb482e0e3ccf72/hourglass_model.py#L43-L45
The intermediate heatmaps should be set as outputs of the model, so it should look something like this:
hg_next_stage, l2s = self.build_network(inputs, trainable=trainable)
self.model = tf.keras.Model(inputs=inputs, outputs=l2s)
But for this to work, the data loader should also repeat the label set for each image STAGE_NUM
times. So that each intermediate output would get its own labels.
Or, am I missing something?
from tf2-mobile-2d-single-pose-estimation.
Thank you, @grin! I've already solved my problem using different approach. But it's interesting to get the clarification!
from tf2-mobile-2d-single-pose-estimation.
Related Issues (20)
- Implement ModelProvider
- Experiments HOT 9
- Evaluate with MPII
- Update README for 1.0.0 HOT 1
- All in one dataset
- Pre-trained Model Release HOT 3
- Add gif demo on README
- Support hand pose estimation dataset
- Set the layer names when release
- Training trend seems weird on COCO Datasets HOT 1
- Update exp001~exper005
- Regarding changing augmentation to improve accuracy HOT 1
- KeyError: 'extra' in train.py
- Model Files Needed
- Filtering COCO keypoint dataset to single person only and convert it HOT 3
- Convert Eager to Keras fit in training HOT 8
- please provide the code python sniplet for getting keypoints from .pb modela and .tflite file
- getting error while running train.py in windows HOT 1
- RAM memory increases
- How can I add Upsampling2D at end of mv2_cpm?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
đ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. đđđ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google â¤ī¸ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tf2-mobile-2d-single-pose-estimation.