Comments (5)
Yes, you are right.
BTW, if you want to resize the CIFAR-10 size, you need to add a "resize transform" at here and also revised the shape at here, which is used to compute the FLOPs.
from nats-bench.
Thanks for your questions.
The code above will direct u to execute these lines, so as to create the macro structure defined in NATS-Bench (https://github.com/D-X-Y/AutoDL-Projects/blob/58733c18becf18cd5c66392eb0ca6a80e2d14d23/xautodl/models/cell_infers/tiny_network.py#L10).
This macro structure will downsample twice and have a global pooling layer before the last FC layer. Therefore, this structure is resolution-agnostic. You can use either 1616 inputs as ImageNet-16-120, or 3232 for CIFAR, or 256*256 for your datasets.
Having said that, for the 256 * 256 input resolution, 2 downsampling layer in the network may not be enough regarding the model capacity. While that is another question.
In sum, so far, the config
u obtained from the above code is resolution-agnostic, u can directly use it for inputs with different resolutions.
from nats-bench.
Thanks for your questions.
The code above will direct u to execute these lines, so as to create the macro structure defined in NATS-Bench (https://github.com/D-X-Y/AutoDL-Projects/blob/58733c18becf18cd5c66392eb0ca6a80e2d14d23/xautodl/models/cell_infers/tiny_network.py#L10).This macro structure will downsample twice and have a global pooling layer before the last FC layer. Therefore, this structure is resolution-agnostic. You can use either 16_16 inputs as ImageNet-16-120, or 32_32 for CIFAR, or 256*256 for your datasets.
Having said that, for the 256 * 256 input resolution, 2 downsampling layer in the network may not be enough regarding the model capacity. While that is another question.
In sum, so far, the
config
u obtained from the above code is resolution-agnostic, u can directly use it for inputs with different resolutions.
Thanks a lot for your fast response.
So, the config below
config = api.get_net_config(12, 'cifar10')
obtains a config appropriate for cifar10 completely agnostic to the pre-defined input resolution in get_datasets function, right? and If I simply resize cifar10 size to e.g. 64 or 128 in the get_datasets function, the appropriate results can still be obtained (except the number of downsampling issue that you mentioned)?
from nats-bench.
Thanks for your questions. The code above will direct u to execute these lines, so as to create the macro structure defined in NATS-Bench (https://github.com/D-X-Y/AutoDL-Projects/blob/58733c18becf18cd5c66392eb0ca6a80e2d14d23/xautodl/models/cell_infers/tiny_network.py#L10).
This macro structure will downsample twice and have a global pooling layer before the last FC layer. Therefore, this structure is resolution-agnostic. You can use either 16_16 inputs as ImageNet-16-120, or 32_32 for CIFAR, or 256*256 for your datasets.
Having said that, for the 256 * 256 input resolution, 2 downsampling layer in the network may not be enough regarding the model capacity. While that is another question.
In sum, so far, the
config
u obtained from the above code is resolution-agnostic, u can directly use it for inputs with different resolutions.
Hi! I was thinking about some changes in my project and I came back to our topic again :)
You mentioned that the structure is resolution-agnostic and I can use 16_16 inputs for my custom datasets with 128x128 resolution. But, wouldn't it reduce the dimensionality of my image in such a way that small objects in it disappear?
+Where and how in here can I increase the number of downsample layers? how many do U suggest for input C of 128 and 256?
- I changed the channel input size by config['C'] = 32 after
config = api.get_net_config(arch, 'cifar10')
.Do you consider changing config['C'] = 32 or any other values is effective way for increasing accuracy for custom datasets with higher resolutions?
Thanks a lot for you help! <3
from nats-bench.
To increase the number of downsample layers, you need to change the definition of TinyNetwork
. Please see here: https://github.com/D-X-Y/AutoDL-Projects/blob/58733c18becf18cd5c66392eb0ca6a80e2d14d23/xautodl/models/cell_infers/tiny_network.py#L21, a True
means a downsample layer.
from nats-bench.
Related Issues (20)
- The reasults of test accuracy HOT 2
- get_cost_info(hp="200") returns weird value for some models in topology search space HOT 4
- Problem recreating api in fastmode HOT 2
- The results of validation/test accuracy in NATS-Bench paper HOT 4
- best accuracy find HOT 3
- The code for ImageNet16 is 404 error HOT 4
- How to generate a architecute model with torch HOT 4
- Question regarding the design space for the topology search space in NATS-Bench HOT 1
- api_utils.py invoking get_latency method without passing "hp" parameter HOT 3
- No testset in ImageNet16 HOT 1
- Details about the data structures more_info and cost_info HOT 2
- Question about ImageNet16120 HOT 1
- Is NATS Extension of NAS_201 bench HOT 4
- get_net_param returns empty dictionary HOT 1
- Regarding the checkpoints HOT 3
- What is the seed of subnet training on cifar10, 111 or 777? HOT 3
- Further training of the network obtained from NATS bench
- Regarding inference with pretrained weights.
- get_more_info(): different seed but same 'train-accuracy', 'train-all-time', 'train-all-time'
- Question about the different init model weights of NATS-Bench-tss and NASbench201
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 nats-bench.