Comments (5)
It seems that tensor2tensor's problem.dataset() has changed and now require the second argument data_dir
not to be left empty.
I could solve the problem by changing demogen/data_util.py
as follows:
def input_data():
"""Input function to be returned."""
prob = problems.problem(problem_name)
data_dir = '<<<MY_HOME_DIRECTORY>>>/t2t_data/';
if data == 'image_cifar100':
dataset = prob.dataset(mode, data_dir, preprocess=augmented)
if not augmented: dataset = dataset.map(map_func=standardization)
else:
dataset = prob.dataset(mode, data_dir)
dataset = dataset.map(map_func=standardization)
and I have previously downloaded the data into this directory using:
t2t-datagen --generate_data --data_dir=~/t2t_data --problem=image_cifar100
t2t-datagen --generate_data --data_dir=~/t2t_data --problem=image_cifar10
from google-research.
Same for me!
Perhaps this is a setup issue of tensorflow-datasets? I didn't configure it to download CIFAR, etc.
from google-research.
Thank you for working this out. I am working on potentially easier way to get the dataset for external users.
from google-research.
Thanks, @yidinggiang! But are you sure the data split into training/validation/test set is determenistic?
That is, that the CIFAR10/100 training set I got is the same as the one used to train the models?
from google-research.
CIFAR10 and 100 have fixed training and test sets, so I don't see any problems. (There have been some changes to the data pipeline, please pull to get them)
from google-research.
Related Issues (20)
- Possible normalization error in Gram-Schmidt orthonormalization process in GPNR
- bug in VRDU evalution code HOT 2
- [SMURF] Port Weights to PyTorch HOT 3
- Google HOT 2
- datasets HOT 5
- J
- [DITO] About train*.tfrecord and val*.tfrecord file HOT 1
- TiDE model loading errors
- [FindIt] Facing issues in running findit.demo
- Is SayCan code in the repo still working?
- [F-VLM] CLIP Recognition Bias
- [ScaNN] missing headers in release 1.2.10 HOT 4
- Discrepancy with CMMD paper HOT 3
- [KWS_Streaming] AttributeError: module 'keras._tf_keras.keras.layers' has no attribute 'LocallyConnected1D' HOT 4
- [slot attention] slots spread over all objects
- SCANN: Error when building from source
- Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).
- Cast string to float is not supported error when running MAVE
- Typo in google-research/misinfo_provenance/model/train.py
- RegNeRF Mesh Export Query
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 google-research.