Comments (5)
Thank you @tushuhei, that worked perfectly! :)
from emoji-scavenger-hunt.
Somehow the issue is gone. I dont know what I did. But I did upgrade the Docker file script to get the latest version of the retrain.py. Training went out smoothly, the models loaded properly, but I get this error when I try to predict
Uncaught (in promise) Error: Missing input placeholders: Placeholder
at GraphExecutor.checkInput (graph_executor.js:253)
at GraphExecutor.execute (graph_executor.js:134)
at FrozenModel.execute (frozen_model.js:161)
at mobilenet.js:49
at Object.Tracking.tidy (tracking.js:36)
at MobileNet.predict (mobilenet.js:36)
at snap.js:69
at Object.Tracking.tidy (tracking.js:36)
at HTMLImageElement.self.PLANT.onload (snap.js:68)
from emoji-scavenger-hunt.
Our script assumes the model input placeholder has the name input
as specified below.
emoji-scavenger-hunt/src/js/mobilenet.ts
Line 28 in c6dbb72
However, it looks like your model has renamed the input placeholder as
Placeholder
instead for some reason. Could you try editing the line above from 'input'
to 'Placeholder'
and running your model again?from emoji-scavenger-hunt.
@oninross how did you upgrade docker files??I am getting same error what should i do..
from emoji-scavenger-hunt.
Hi nidhishgandhi,
From seeing the error saying "Label yawning has no images in the category training", I assume it's caused by a lack of images for training. Could you check if there are multiple images under data/images/yawning
directory? Please refer to https://github.com/google/emoji-scavenger-hunt#build-your-own-model for more details about data setup.
from emoji-scavenger-hunt.
Related Issues (20)
- Is it working on Android ? HOT 17
- I play the game with my own trained model. But it can't identify objects. HOT 6
- Trying to Build your own model but returns an error HOT 10
- New Logo HOT 1
- Running the docker command returns error HOT 6
- Error when creating bottlenecks HOT 2
- Detecting Retrained Data HOT 2
- QR code
- New Models trained but getting "Argument 'b' passed to 'mul' must be a Tensor, but got undefined." after trying to start the game.
- Training new models HOT 2
- cannot run it ... HOT 1
- Number of Objects Trained HOT 2
- "Browser or device doesn't support this experiment"? HOT 6
- Original training data set
- Running docker returns errors regarding Tensorflow HOT 3
- how to compress the tensorflowjs_model.pb in 54kb
- Session bundle and Frozen model formats have been deprecated in TensorFlow.js 1.0. How do I generate model comparable with new tfjs api? HOT 1
- Can't open the pb file
- How to proper install it and run
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from emoji-scavenger-hunt.