Comments (4)
Hi @vglsd , thanks for your interest in our work and MMGEN
.
I suggest that you may visualize the generated samples first. Since FID=19
indicates a poor generation quality, you can check whether the output samples indeed show any artifacts.
from mmgeneration.
Thanks for the prompt reply!
I realized the FID gets worse when I use truncation on the noise input. Did you use any truncation in the results you report?
Moreover, just to make sure I am not making any mistake on this:
python tools/utils/inception_stat.py --imgsdir ${path-to-1024-FFHQ} --pklname ${out-pkl-destination} --size ${size-of-output-images-to-compare-with} --num-samples 50000
Is this the right command to get the inception pkl?
from mmgeneration.
There are some mistakes in your command:
- Firstly, you should explicitly resize the 1024-FFHQ dataset to 256-FFHQ dataset. Then, the
--imgsdir
should be set with the path for the256-FFHQ
. --size
will set the size of input images to the inception network. In general, the input shape of the pre-trained inception network should be (299, 299), which is our default setting intools/utils/inception_stat.py
We have already provided the 256-FFHQ inception stat, which you can download from here.
We did NOT use any truncation tricks in calculating quantitative metrics. In GAN literature, we merely use the truncation trick to perform visualization.
from mmgeneration.
Thanks for the help!
from mmgeneration.
Related Issues (20)
- Latent-Diffusion Models HOT 7
- the Noise Injection method of styleGANv1 is different from StyleGANv2 HOT 2
- RuntimeError: fused_bias_leakyrelu_op_impl: implementation for device cuda:0 not found. HOT 1
- "assert self.is_domain_reachable"
- DDPM training problem HOT 1
- [Bug] Non-distributed Training Error HOT 5
- [Bug] Error with "Positional Encoding as Spatial Inductive Bias in GANs" inference result have artifact HOT 1
- RuntimeError: ModuleNotFoundError: No module named 'matplotlib.blocking_input'
- [Feature] mmgeneration support High dynamic range(HDR) imaging based Deep learning? HOT 1
- Can't work on device cuda:1
- [New Models] Wav2Lip
- [Bug] subprocess.CalledProcessError: Command 'gcc --version | head -n1' returned non-zero exit status 255.
- There is a discrepancy in the results when reproducing the facades in cyclegan, and the FID and IS are inconsistent with the provided ones
- About train by epoch
- How to modify the configuration file when using styleganv2 to generate a single-channel 800x800 SAR image?
- [Feature] How to generate images from my own dataset by DCGAN?
- [Bug] 安装错误 HOT 1
- [New Models] HOT 1
- MMCV版本问题 HOT 1
- in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
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 mmgeneration.