Comments (5)
Hi, for demo, please put latest_net_Flow.pth
for opt.flownet_path
(or you can specify opt.flownet_path=''
as well, because it will load the saved checkpoints later anyway.)
For training, please put the pre-trained flownet for opt.flownet_path
. If you don't want to train the flownet by yourself, you can also extract the flownet weight from GFLA by:
- Download weights of Pose-Guided Person Image Generation (the weights trained on fashion dataset.)
- Then extract the flownet weights from the
latest_net_G.pth
(the weight of the full GFLA model) by something like
import torch
weights = torch.load("latest_net_G.pth")
flownet_weights = {w.replace("flow_net.",""): weights[w] for w in weights if w.startswith("flow_net")}
torch.save(flownet_weights, "flownet.pth")
Note GFLA is trained on 256x256 images.
from dressing-in-order.
Thanks for your answer o( ̄▽ ̄)ブ
from dressing-in-order.
Thanks for your answer, and I also can't find the flownet.opt file, so if there is the url for flownet.opt will be better
from dressing-in-order.
Thanks for your answer, and I also can't find the flownet.opt file, so if there is the url for flownet.opt will be better
There is no need to replay my question, and I have already got it, and also thank you very much about your idea
from dressing-in-order.
First of all, there was a issue regarding "flownet.pt" not fund, I resolved it by using opt.flownet_path='' but unfortunately now this issue arrised. What can I do ?
load vgg ckpt from torchvision dict.
[init] init pre-trained model vgg.
initialize network with orthogonal
initialize network with orthogonal
initialize network with kaiming
initialize network with orthogonal
[init] frozen net netVGG.
[init] frozen net netFlow.
[init] frozen net netE_attr.
[init] frozen net netE_attr.
not exsits checkpoints/DIOR_64/latest_net_E_attr.pth
not exsits checkpoints/DIOR_64/latest_net_G.pth
not exsits checkpoints/DIOR_64/latest_net_VGG.pth
not exsits checkpoints/DIOR_64/latest_net_Flow.pth
---------- Networks initialized -------------
[Network E_attr] Total number of parameters : 1.191 M
[Network G] Total number of parameters : 16.501 M
[Network VGG] Total number of parameters : 0.113 M
[Network Flow] Total number of parameters : 6.608 M
FileNotFoundError Traceback (most recent call last)
in ()
30 # create model
31 model = DIORModel(opt)
---> 32 model.setup(opt)
1 frames
/content/drive/MyDrive/Virtual Fitting Room/dressing-in-order-main/models/base_model.py in _init_tensorboard(self, opt)
146 if os.path.exists(self.tb_dir):
147 shutil.rmtree(self.tb_dir)
--> 148 os.mkdir(self.tb_dir)
149 self.image_dir = os.path.join(self.tb_dir, "images")
150 os.makedirs(self.image_dir, exist_ok=True)
FileNotFoundError: [Errno 2] No such file or directory: 'checkpoints/DIOR_64/test'
from dressing-in-order.
Related Issues (20)
- Can this change of clothes work for everyone? HOT 1
- FID value less than paper HOT 4
- Testing with custom images of garment only HOT 4
- What's the version of openpose? HOT 1
- Where is pretrained model?? HOT 1
- How to Train on High Resolution HOT 2
- No images are printed: HOT 1
- the groups and the persons in them HOT 1
- The Categories HOT 1
- Test Custom Images HOT 2
- Testing on CPU HOT 4
- Human Parser Issue HOT 2
- Dataset password required to run inference in demo? HOT 1
- Pose Transfer output image is empty HOT 1
- Bad results by the pre-trained model when tested on an unseen image HOT 2
- Traninig models on Viton datasets HOT 1
- Texture transfer results HOT 1
- correct dimension for testing on custom dataset HOT 3
- Input Issues HOT 3
- no images show 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 dressing-in-order.