Comments (7)
@Noplz @shicai You were right, I made a mistake. I fixed it in this commit 40f4f7e
@aussetg A more refactored version is available in Tensorflow https://github.com/taehoonlee/tensornets/blob/master/tensornets/nasnets.py
However, it was easier for me to create CellStem0, CellStem1, Cell0, Cell1 and ReductionCell0 regarding my will to port the pretrained parameters from tensorflow after my deadline (15 nov).
By the way I mainly used tensorboard.
from pretrained-models.pytorch.
@rkaplan @Noplz @aussetg Done ! 247b037
from pretrained-models.pytorch.
@Noplz I think you are right. it should be max pooling for comb_iter_1_left
and average pooling for comb_iter_2_left
.
from pretrained-models.pytorch.
I also don't understand why there are Cell1 and Cell0, the original paper only includes one type of Normal Cell, and one type of Reduction Cell
from pretrained-models.pytorch.
@Cadene How do you port weights from TensorFlow?
Also I don't think the TF weights are sota, they don't implement path wise dropout like in the paper ( probably because they can't with TensorFlow as the graph then changes at every iteration. But then I wonder what framework the Google team used ๐ )
from pretrained-models.pytorch.
@Cadene great job anyway, this repo is really helpful :) ๐
from pretrained-models.pytorch.
Congrats on finishing your deadline :) just wanted to say thank you for working on this NASNet port, looking forward to trying it out!
from pretrained-models.pytorch.
Related Issues (20)
- why there no avgpooling๏ผ HOT 1
- What parameters should I use to reproduce the pre-training process of ResNet18
- Why InceptionResnetV2 has 1536 output feature maps HOT 1
- Can I use these pretrained models with the same input shape?
- Issue with Downloading Pretrained models
- VGG model.features HOT 1
- Problem with using model se_resnext50
- The se-resnet_50 model has either have corrupted weights or is an incomplete one!
- Error: unexpected EOF, expected 867442 more bytes. The file might be corruptedls.__dict__[model_name](num_classes=1000, pretrained='imagenet') model.eval()
- Pretrained model paths HOT 1
- error with pip install or git clone on kaggle kernel
- Requesting pre-trained model variants trained on grayscale ImageNet HOT 9
- What are the differences between files with difference hashes?
- HTTPError: HTTP Error 503: Service Unavailable when loading se_resnet50 weights
- DeprecationWarning: BILINEAR is deprecated and will be removed in Pillow 10 HOT 1
- SSL certificate is expired HOT 2
- Deprecated Warning of torchvision "pretrained"
- ModuleNotFoundError: No module named 'six' HOT 1
- The forward contains irrelevant attributes. HOT 1
- Need a pre-trained grayscale image net
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pretrained-models.pytorch.