minar09 / acgpn Goto Github PK

I have searched the entire repo but still couldn't find the solution for the above error.
Any solution for this ?
File "train.py", line 168, in <module> loss_dict = dict(zip(model.module.loss_names, losses)) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 772, in __getattr__ type(self).__name__, name)) torch.nn.modules.module.ModuleAttributeError: 'Pix2PixHDModel' object has no attribute 'module'

Thanks heaps for your good working replicating ACGPN inference model. One problem I am working on is that when I train it with VITON dataset (lip segmentation inputs with 20 labels), I found:

1. The train.py forward pass inputs are different from their original model. Is there a specific reason for this change (one input data['image']  removed)?
   

2. When I use lip dataset for training, I ran into this error:
   

Based on this report: NVlabs/SPADE#57, it should be a channel mismatch problem. However, I believe all relevant channels had been mapped to LIP except channel 7 (noise channel). The thing is that there is no counterpart in LIP label for this channel (I used a coat channel but not work apparently). Any recommendation for fixing this issue?

Thank you very much for contributing to this amazing project.

I am trying to test the model with custom images and I have:

• test_color
• test_edge
• test_img
• test_label
• test_pose

How can you generate the files from the folders ?:

• test_mask
• tes_colormask

Thanks

Hi, I'm trying to dress one person with some specific clothes in this dataset. However, when I run test.py, the result seems every person is dressed randomly by the clothes in file img_color. How can I dress specific clothes for a person. Thank you very much!

Thank you for your great job!
However, the training script of this repository does not work.
I meet the ValueError when run python train.py.
In line 161 of the train.py,

ValueError: not enough values to unpack (expected 16, got 10)

I checked the models/pix2pixHD_model.py.
Thus, the forward function of pix2pixHD_model.py returns only 10 arguments.
Now, I confirm the Unet class of the models/networks.py does not return rx, ry, cx, and cy arguments.
After that, I add the rx, ry, cx, and cy arguments to the return function of the forward function of the Unet class.

However, I cannot find refined, rg, and cg arguments of line 161 of the train.py.

Please fix the training scripts so it works.
Thanks.

Thank you for the repository, is there any browser implementation of the model and if not then is it possible to make it run on the client side ? since the pipeline contains various model will it cause issue.

I have tried your code and it is working fine but I want to run the code on custom images , how it is possible ?

Traceback (most recent call last):
File "E:\Virtual try on\ACGPN-master\test.py", line 122, in
main()
File "E:\Virtual try on\ACGPN-master\test.py", line 97, in main
fake_image, warped_cloth, refined_cloth = model(Variable(data['label'].cuda()), Variable(data['edge'].cuda()), Variable(img_fore.cuda()), Variable(
File "C:\Users\SM\AppData\Roaming\Python\Python39\site-packages\torch\nn\modules\module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "E:\Virtual try on\ACGPN-master\models\pix2pixHD_model.py", line 492, in forward
return self.inference(label, pre_clothes_mask, img_fore, clothes_mask, clothes, all_clothes_label, real_image, pose, grid, mask_fore)
File "E:\Virtual try on\ACGPN-master\models\pix2pixHD_model.py", line 384, in inference
input_label, masked_label, all_clothes_label = self.encode_input(
File "E:\Virtual try on\ACGPN-master\models\pix2pixHD_model.py", line 233, in encode_input
1, (label_map * (1 - clothes_mask)).data.long().cuda(), 1.0)
File "C:\Users\SM\AppData\Roaming\Python\Python39\site-packages\torch\tensor.py", line 528, in rsub
return _C._VariableFunctions.rsub(self, other)
RuntimeError: CUDA error: device-side assert triggered

How can I fix this issue?

when i train, i can't find train_pairs.txt in ./Data_preprocessing directory?

I have started training the model on viton dataset. till now i have trained for 4 epochs it is showing 15 days more means how much epoch more is required to complete the training process.
Can training the model again on MPV dataset is useful for better results.

All needed softwares are installed
Here's the screenshot: https://i.hizliresim.com/AxQ7g7.png

@minar09 Hello thank you for providing the code for testing this model

But I'm facing this error while running the test.py

can you please help me with it?

Thank you

hello again, thank you very much for the previous answer.

I am trying to run the test.py file with custom images and I am getting the following error:

File "test.py", line 126, in
main()
File "test.py", line 103, in main
mask_clothes.cuda()), Variable(data['color'].cuda()), Variable(all_clothes_label.cuda()), Variable(data['image'].cuda()), Variable(data['pose'].cuda()), Variable(data['image'].cuda()), Variable(mask_fore.cuda()))
File "/home/josearangos/anaconda3/envs/torch_env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/josearangos/Documentos/Clothe_mE/repositorios/versions_DeepFashion_Try_On/ACGPN/models/pix2pixHD_model.py", line 493, in forward
return self.inference(label, pre_clothes_mask, img_fore, clothes_mask, clothes, all_clothes_label, real_image, pose, grid, mask_fore)
File "/home/josearangos/Documentos/Clothe_mE/repositorios/versions_DeepFashion_Try_On/ACGPN/models/pix2pixHD_model.py", line 388, in inference
(label.cpu().numpy() == 11).astype(np.float)).cuda()
RuntimeError: cuda runtime error (59) : device-side assert triggered at /pytorch/aten/src/THC/generic/THCTensorCopy.cpp:70

Thank you for helping me

Hi,
Thank you for this repo. This work pretty nicely.
I am trying to test this on different images of my own
So, how can I generate test_label, test_pose and test_edge folders given human image in test_img folder and dress image in test_color folder.

@minar09 Thanks for share you ideas, I admire you a lot, Receive my regards

Hi, I want to share the code with i generated the mask for the clothes

import numpy as np
import cv2
from matplotlib import pyplot as plt


PATH_IMG ="5.jpg"
image = cv2.imread(PATH_IMG)
mask = np.zeros(image.shape[:2], dtype="uint8")
rect = (1, 1, mask.shape[1], mask.shape[0])
fgModel = np.zeros((1, 65), dtype="float")
bgModel = np.zeros((1, 65), dtype="float")
start = time.time()
(mask, bgModel, fgModel) = cv2.grabCut(image, mask, rect, bgModel,
                                       fgModel, iterCount=10, mode=cv2.GC_INIT_WITH_RECT)
outputMask = np.where((mask == cv2.GC_BGD) | (mask == cv2.GC_PR_BGD),0, 1)
outputMask = (outputMask * 255).astype("uint8")


plt.imshow(image)
plt.title('my picture')
plt.show()

plt.imshow(outputMask, cmap="gray")

Is there any implementation available for the difficulty function?

Hi, Great work, and thanks for sharing. can I use the PGN_tf parsing model and use the output in this model? currently, I'm using the U^2 net mode to generate the masks.
I'd appreciate it if you could guide me to test this model on custom images.

Hi, I'm trying to dress one person with some specific clothes in this dataset. However, when I run test.py, the result seems every person is dressed randomly by the clothes in file img_color. How can I dress specific clothes for a person. Thank you very much!

Hi, so I saw the paper wherein they have made full sleeves Tryon given a model wearing half sleeves clothing. But, I am not able to generate that.

Note that, it is working the other way around.

What parameters do I need to change?

Hi,

Can you let me know how to use mutilGPU on this code? I checked netwoeks.py, all networks are assigned to model.cuda(gpus_id[0]). By model.cuda(gpus_id), does the network works on gpus or I need to do

model = nn.DataParallel(model) as well?

I trying to train the model but I get an error at line 160 for train.py. How do I fix that?

There is a small error in file data/aligned_dataset.py line 203. There should be
'name': A_path.split("/")[-1].split("\")[0]