Comments (5)
original_ddim_ddpm = False
num_unet = 2
objective = 'pred_res_noise'
test_res_or_noise = "res_noise"
if original_ddim_ddpm:
model = Unet(
dim=64,
dim_mults=(1, 2, 4, 8)
)
diffusion = GaussianDiffusion(
model,
image_size=image_size,
timesteps=1000, # number of steps
sampling_timesteps=sampling_timesteps_original_ddim_ddpm,
loss_type='l1', # L1 or L2
)
else:
model = UnetRes(
dim=64,
dim_mults=(1, 2, 4, 8),
num_unet=num_unet,
condition=condition,
input_condition=input_condition,
objective=objective,
test_res_or_noise=test_res_or_noise
)
diffusion = ResidualDiffusion(
model,
image_size=image_size,
timesteps=1000, # number of steps
# number of sampling timesteps (using ddim for faster inference [see citation for ddim paper])
sampling_timesteps=sampling_timesteps,
objective=objective,
loss_type='l2', # L1 or L2
condition=condition,
sum_scale=sum_scale,
input_condition=input_condition,
input_condition_mask=input_condition_mask,
test_res_or_noise=test_res_or_noise
)
这是我的配置
from rddm.
请问您是用多少张卡训练的
from rddm.
感谢大家关注RDDM。去噪可以参考一下另一个issue,https://github.com/nachifur/RDDM/issues/2。
单卡3090就可以跑论文里绝大多数的实验。
抱歉,这几天事情比较多,过段时间会更新代码。
from rddm.
8g显存的卡一个batchsize能跑起来
from rddm.
8g显存的卡一个batchsize能跑起来
好的,感谢您
from rddm.
Related Issues (20)
- 关于训练的一些疑问 HOT 11
- 关于image translation的一些疑问 HOT 4
- 关于图像恢复任务的时间步修改 HOT 1
- Low-Light Experimental settings HOT 9
- ./experiments/convert_pretrained_DDIM_to_RDDM/src/路径下两个.py文件缺少了一些导入代码 HOT 3
- pre-trained ckpt HOT 6
- 下载的文件的压缩包只有3kb,想问这个源文件能手动下载吗?
- 数据集划分 HOT 2
- .flist无法识别 HOT 3
- GOPRO的训练数据选择的问题 HOT 1
- 尊敬的作者您好!想请问一下关于训练的问题 HOT 1
- Questions about #params and flops HOT 2
- cannot find the part HOT 2
- 图像生成任务的默认设置问题 HOT 2
- 关于ReadMe中的取消注释同时预测noise和res的疑问 HOT 2
- 关于条件生成问题 HOT 1
- 关于ddim_sample中的type == "special_eta_0"和type == "special_eta_1" HOT 1
- 图像恢复 HOT 1
- 深度估计任务 HOT 1
- 使用不配对的数据进行训练 HOT 1
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 rddm.