hanzhanggit / stackgan-v2 Goto Github PK

I am running this on a MacBook Pro (Retina, 13-inch, Early 2015) macOS Catalina 10.15.3 GPU Intel Iris Graphics 6100 1536 MB
I am at this step in the instructions: python main.py --cfg cfg/birds_3stages.yml --gpu 0

And I get this as a result:
/Users/f00l/Desktop/GitHubProject/StackGAN-v2/code/miscc/config.py:103: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yaml_cfg = edict(yaml.load(f))
Using config:
{'CONFIG_NAME': '3stages',
'CUDA': False,
'DATASET_NAME': 'birds',
'DATA_DIR': '../data/birds',
'EMBEDDING_TYPE': 'cnn-rnn',
'GAN': {'B_CONDITION': True,
'DF_DIM': 64,
'EMBEDDING_DIM': 128,
'GF_DIM': 64,
'NETWORK_TYPE': 'default',
'R_NUM': 2,
'Z_DIM': 100},
'GPU_ID': '0',
'TEST': {'B_EXAMPLE': True, 'SAMPLE_NUM': 30000},
'TEXT': {'DIMENSION': 1024},
'TRAIN': {'BATCH_SIZE': 24,
'COEFF': {'COLOR_LOSS': 0.0, 'KL': 2.0, 'UNCOND_LOSS': 1.0},
'DISCRIMINATOR_LR': 0.0002,
'FLAG': True,
'GENERATOR_LR': 0.0002,
'MAX_EPOCH': 600,
'NET_D': '',
'NET_G': '',
'SNAPSHOT_INTERVAL': 2000,
'VIS_COUNT': 64},
'TREE': {'BASE_SIZE': 64, 'BRANCH_NUM': 3},
'WORKERS': 4}
/Users/f00l/Desktop/GitHubProject/StackGAN-v2/venv/lib/python2.7/site-packages/torchvision/transforms/transforms.py:156: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead.
"please use transforms.Resize instead.")
Total filenames: 11788 001.Black_footed_Albatross/Black_Footed_Albatross_0046_18.jpg
Load filenames from: ../data/birds/train/filenames.pickle (8855)
embeddings: (8855, 10, 1024)
Traceback (most recent call last):
File "main.py", line 140, in
algo = trainer(output_dir, dataloader, imsize)
File "/Users/f00l/Desktop/GitHubProject/StackGAN-v2/code/trainer.py", line 537, in init
torch.cuda.set_device(self.gpus[0])
File "/Users/f00l/Desktop/GitHubProject/StackGAN-v2/venv/lib/python2.7/site-packages/torch/cuda/init.py", line 262, in set_device
torch._C._cuda_setDevice(device)
AttributeError: 'module' object has no attribute '_cuda_setDevice'

How do I fix this?

The main.py use the birds_proGAN.yml file, but I can't find it in the project

So I have followed all the steps necessary till the training of the StackGAN on the birds dataset but I am receiving a memory allocation error while training. I will enclose the Colab link I am using as well as the detailed error statement for your convenience. Any help would be deeply appreciated. Thank you!
Regards,
Parth Rangarajan.
Here is the collaboratory link: https://colab.research.google.com/drive/1ASXNdAWI54x8zXZROHcYhkhEX8ciK8-H?usp=sharing

Here is the error:
Using config: {'CONFIG_NAME': '3stages', 'CUDA': True, 'DATASET_NAME': 'birds', 'DATA_DIR': '../data/birds', 'EMBEDDING_TYPE': 'cnn-rnn', 'GAN': {'B_CONDITION': True, 'DF_DIM': 64, 'EMBEDDING_DIM': 128, 'GF_DIM': 64, 'NETWORK_TYPE': 'default', 'R_NUM': 2, 'Z_DIM': 100}, 'GPU_ID': '0', 'TEST': {'B_EXAMPLE': True, 'SAMPLE_NUM': 30000}, 'TEXT': {'DIMENSION': 1024}, 'TRAIN': {'BATCH_SIZE': 24, 'COEFF': {'COLOR_LOSS': 0.0, 'KL': 2.0, 'UNCOND_LOSS': 1.0}, 'DISCRIMINATOR_LR': 0.0002, 'FLAG': True, 'GENERATOR_LR': 0.0002, 'MAX_EPOCH': 600, 'NET_D': '', 'NET_G': '', 'SNAPSHOT_INTERVAL': 2000, 'VIS_COUNT': 64}, 'TREE': {'BASE_SIZE': 64, 'BRANCH_NUM': 3}, 'WORKERS': 4} /usr/local/lib/python3.7/dist-packages/torchvision/transforms/transforms.py:310: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead. warnings.warn("The use of the transforms.Scale transform is deprecated, " + Total filenames: 11788 001.Black_footed_Albatross/Black_Footed_Albatross_0046_18.jpg Load filenames from: ../data/birds/train/filenames.pickle (8855) tcmalloc: large alloc 65850621952 bytes == 0x5631f8284000 @ 0x7fd36b19a001 0x7fd274fd754f 0x7fd275027b58 0x7fd27502ae83 0x7fd27502b07b 0x7fd2750cc761 0x5631778c24b0 0x5631778c2240 0x5631779360f3 0x5631778c3afa 0x563177931c0d 0x5631779309ee 0x5631778c448c 0x563177905159 0x5631779020a4 0x5631778c2d49 0x56317793694f 0x5631779309ee 0x5631779306f3 0x5631779fa4c2 0x5631779fa83d 0x5631779fa6e6 0x5631779d2163 0x5631779d1e0c 0x7fd369f82bf7 0x5631779d1cea ^C

def KL_loss(mu, logvar):
# -0.5 * sum(1 + log(sigma^2) - mu^2 - sigma^2)
KLD_element = mu.pow(2).add_(logvar.exp()).mul_(-1).add_(1).add_(logvar)
KLD = torch.mean(KLD_element).mul_(-0.5)
return KLD

Can anyone clearly explain how do we prepare the dataset. I've refered many issues but dataset preparation is still unclear.

Hi,

I have used a script from another StackGAN repo to generate embeddings for sentences. The result for a set of sentences when I load in the t7 file and convert it numpy is a 2D matrix - where there is a 1 dimensional embedding for each sentence - this is to be expected.

However, when I look at the code for this repo is shows the below reference:
t_embeddings[:, i, :]

indicating that t_embeddings is 3D - where does the extra dimension come from?

Hello, I was training the bird dataset with the command python3 main.py --cfg cfg/birds_3stages.yml --gpu 0 and these two errors occurred. This happened after the 2nd epoch of the training. Does anyone know anything about these errors and how to fix them?

NOTE:
I am using python version 3.5

Thank you.

Traceback (most recent call last):
File "main.py", line 146, in
algo.evaluate(split_dir)
File "/home/user/Downloads/StackGAN-v2-master/code/trainer.py", line 874, in evaluate
fake_imgs, _, _ = netG(noise, t_embeddings[:, i, :])
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/parallel/data_parallel.py", line 121, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/user/Downloads/StackGAN-v2-master/code/model.py", line 275, in forward
h_code3 = self.h_net3(h_code2, c_code)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/user/Downloads/StackGAN-v2-master/code/model.py", line 215, in forward
out_code = self.upsample(out_code)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/container.py", line 91, in forward
input = module(input)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/modules/batchnorm.py", line 66, in forward
exponential_average_factor, self.eps)
File "/home/user/anaconda2/envs/stackGANv2/lib/python2.7/site-packages/torch/nn/functional.py", line 1254, in batch_norm
training, momentum, eps, torch.backends.cudnn.enabled
RuntimeError: CUDA error: out of memory

Hi,
  may you supply the char-CNN-RNN text embeddings and Pretrained Models download links in Baidu Yun drive (https://pan.baidu.com/ )?
  Thanks!

Can we get a demo file for StackGAN-v2 please?

Hi, I have an error when importing protobuf. Anyone know how to deal with it? Really appreciate it.

embeddings: (8855, 10, 1024)
Traceback (most recent call last):
File "main.py", line 139, in
from trainer import condGANTrainer as trainer
File "/home/lby/Desktop/StackGAN-v2/code/trainer.py", line 19, in
from tensorboard import summary
File "/home/lby/anaconda3/envs/GAN/lib/python2.7/site-packages/tensorboard/init.py", line 4, in
from .writer import FileWriter, SummaryWriter
File "/home/lby/anaconda3/envs/GAN/lib/python2.7/site-packages/tensorboard/writer.py", line 23, in
from .src import event_pb2
File "/home/lby/anaconda3/envs/GAN/lib/python2.7/site-packages/tensorboard/src/event_pb2.py", line 6, in
from google.protobuf import descriptor as _descriptor
File "/home/lby/anaconda3/envs/GAN/lib/python2.7/site-packages/google/protobuf/descriptor.py", line 113
class DescriptorBase(metaclass=DescriptorMetaclass):
^
SyntaxError: invalid syntax

RuntimeError: cuda runtime error (10) : invalid device ordinal at torch/csrc/cuda/Module.cpp:32

Please tell me how to solve this problem?

It's really helpful that you provided this, especially with the pre-extracted text features for the birds. Could you also link to the pre-extracted text features for ImageNet and LSUN? Or at least where the raw captions are, so we can run the extractor ourselves? Thanks!

Hi I am running the code but an error occurs:

Traceback (most recent call last):
File "main.py", line 144, in
algo.train()
File "/home/zzw/program/text2img/StackGAN-v2/code/trainer.py", line 755, in train
count, self.image_dir, self.summary_writer)
File "/home/zzw/program/text2img/StackGAN-v2/code/trainer.py", line 206, in save_img_results
sup_real_img = summary.image('real_img', real_img_set)
File "/usr/local/lib/python2.7/dist-packages/tensorboard/summary.py", line 179, in image
image = make_image(tensor, height, width, channel)
File "/usr/local/lib/python2.7/dist-packages/tensorboard/summary.py", line 186, in make_image
output = StringIO.StringIO()
AttributeError: class StringIO has no attribute 'StringIO'

I am using python 2.7 and tensorboard1.0.0a6, and it seems like something wrong with the tensorboard version, could anybody help me?

When running main.py on the birds dataset, I get an error:

IOError: [Errno 2] No such file or directory: u'../data/birds/train/filenames.pickle'

How is /data/birds/train/filenames.pickle generated? I downloaded the CUB_200_2011 dataset and unzipped into /data/birds/CUB_200_2011

Thank you

i am trying to use my own dataset on this GAN model, can you please give me some advice on how to pre-process the dataset images and text to make it fit the model

I am getting the above error please help!

[219/600][368]
Loss_D: 1.21 Loss_G: 47.18 Loss_KL: 9.08 Time: 264.67s

/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [0,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [1,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [2,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [3,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [4,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [5,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [6,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [7,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [8,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [9,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [10,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [11,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [12,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [13,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [14,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [15,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [16,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [17,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [18,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [19,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [20,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [21,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [22,0,0] Assertion input >= 0. && input <= 1. failed.
/pytorch/aten/src/THCUNN/BCECriterion.cu:42: Acctype bce_functor<Dtype, Acctype>::operator()(Tuple) [with Tuple = thrust::detail::tuple_of_iterator_references<thrust::device_reference, thrust::device_reference, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type, thrust::null_type>, Dtype = float, Acctype = float]: block: [0,0,0], thread: [23,0,0] Assertion input >= 0. && input <= 1. failed.
Traceback (most recent call last):
File "main.py", line 146, in
algo.train()
File "/home/wt/pycharmprojects/StackGAN-v2-master/code/trainer.py", line 733, in train
errD = self.train_Dnet(i, count)
File "/home/wt/pycharmprojects/StackGAN-v2-master/code/trainer.py", line 596, in train_Dnet
errD_wrong = criterion(wrong_logits[0], fake_labels)
File "/usr/local/anaconda3/envs/wtstackgan/lib/python2.7/site-packages/torch/nn/modules/module.py", line 493, in call
result = self.forward(*input, **kwargs)
File "/usr/local/anaconda3/envs/wtstackgan/lib/python2.7/site-packages/torch/nn/modules/loss.py", line 512, in forward
return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
File "/usr/local/anaconda3/envs/wtstackgan/lib/python2.7/site-packages/torch/nn/functional.py", line 2113, in binary_cross_entropy
input, target, weight, reduction_enum)
RuntimeError: reduce failed to synchronize: device-side assert triggered

I try to reproduce the code but get stuck in cuda out of memory error when loading Inception-v3 model.

I tried both on a Windows 10 PC with Nvidia 1060X graphic card (6G) and a Linux server with Nvidia Geforce Titan Graphic card (12G). But both time I ran out of memory with the following message:

THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCStorage.cu line=58 error=2 : out of memory Traceback (most recent call last): File "main.py", line 144, in <module> algo.train() File "/backup1/lingboyang/StackGANv2/code/trainer.py", line 666, in train self.inception_model, start_count = load_network(self.gpus) File "/backup1/lingboyang/StackGANv2/code/trainer.py", line 126, in load_network netsD[i] = torch.nn.DataParallel(netsD[i], device_ids=gpus) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 59, in __init__ self.module.cuda(device_ids[0]) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 216, in cuda return self._apply(lambda t: t.cuda(device)) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 146, in _apply module._apply(fn) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 146, in _apply module._apply(fn) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 152, in _apply param.data = fn(param.data) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 216, in <lambda> return self._apply(lambda t: t.cuda(device)) File "/home/vcl/anaconda3/envs/pytorch/lib/python3.6/site-packages/torch/_utils.py", line 69, in _cuda return new_type(self.size()).copy_(self, async) RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCStorage.cu:58

Is this normal? @hanzhanggit Could you tell me what's the minimal hardware requirement to run this program? Is there any way to save graphic memory? Thanks!

Hi，I'm very interested in your work. And I followed everything in README. However，when I evaluate the model(using the birds dataset) I've trained myself with 600 epochs， I even could not get any image have a blurry bird on it， all the images just have one single color without any pattern. And when I use tensorboard， I found that it could not converge. So I'm very confused， is there anything wrong or the training not enough？

I tried StackGANv2, but in a horrible library version I could not move it differently.

Did you tell us the version of the following library of StackGANv2 moved environment?

• tensorflow
• tensorboard

Because I cant import

from tensorboard import FileWriter

Traceback (most recent call last):
File "C:\Users\suman\OneDrive\Documents\StackGan-2\code\main.py", line 144, in
algo.train()
File "C:\Users\suman\OneDrive\Documents\StackGan-2\code\trainer.py", line 756, in train
save_img_results(self.imgs_tcpu, self.fake_imgs, self.num_Ds,
File "C:\Users\suman\OneDrive\Documents\StackGan-2\code\trainer.py", line 207, in save_img_results
sup_real_img = summary.image('real_img', real_img_set).convert('RGB')
File "C:\Users\suman\AppData\Local\Programs\Python\Python310\lib\site-packages\tensorboardX\summary.py", line 287, in image
image = make_image(tensor, rescale=rescale)
File "C:\Users\suman\AppData\Local\Programs\Python\Python310\lib\site-packages\tensorboardX\summary.py", line 329, in make_image
image = Image.fromarray(tensor)
File "C:\Users\suman\AppData\Local\Programs\Python\Python310\lib\site-packages\PIL\Image.py", line 2955, in fromarray
raise TypeError("Cannot handle this data type: %s, %s" % typekey) from e
TypeError: Cannot handle this data type: (1, 1, 260), |u1

This line is causing the error --> sup_real_img = summary.image('real_img', real_img_set)

Is it alright to replace nn.upsampling and conv by ConvTransposed2d in upsampling blocks?
If not, what's the difference between them?

I want to know how to take my own text instead of captions in birds validation set as input to generate an image.

I am trying to implement your work without using CUDA, because I don't have GPU of NVIDIA but working in gaming PC with 32GB RAM.

Hi,

I am trying to run your code, but I keep getting this error:
```RuntimeError: CUDA error: CUBLAS_STATUS_INTERNAL_ERROR when calling `cublasCreate(handle)````

I am using:
CUDA Version: 11.0
Driver Version: 450.66

Could the CUDA version be the source of the problem?

Thanks

Say i have a dataset of dogs or cats or something,

Can i run StackGAN, as coded currently, to not use the text embeddings? (i.e., not stack the embedding vector and ignore the conditional loss)

thanks

I have been trying to install it from the link below for 3 days now. But my request is still not approved. How can I download it if maybe the author is busy and not looking at my request?
https://drive.google.com/open?id=0B3y_msrWZaXLT1BZdVdycDY5TEE

torch.cuda.set_device(self.gpus[0])

File "/home/txl/TF-Projects/GAN/StackGAN-v2-master/code/trainer.py", line 20, in
from tensorboard import FileWriter
ImportError: cannot import name FileWriter

I found that tensorboard has no model named FileWriter.
anyone can tell me how to resolve this problem ?

1x TITAN XP，260s/epoch ( birds_3stages )
2x TITAN XP，240s/epoch ( birds_3stages )
3x TITAN XP，220s/epoch ( birds_3stages )

Are those images available publicly?

Traceback (most recent call last):
File "main.py", line 150, in
algo.train()
File "/disk/StackGAN-v2-master/code/trainer.py", line 347, in train
self.inception_model, start_count = load_network(self.gpus)
File "/disk/StackGAN-v2-master/code/trainer.py", line 132, in load_network
state_dict = torch.load(cfg.TRAIN.NET_G)
File "/usr/local/lib/python2.7/dist-packages/torch/serialization.py", line 358, in load
return _load(f, map_location, pickle_module)
File "/usr/local/lib/python2.7/dist-packages/torch/serialization.py", line 531, in _load
magic_number = pickle_module.load(f)
EOFError

Help me to calculate Human Ranking (HR) score of GAN model.

hi, why do you update G by avg_param_G? like this

In these lines, we see that discriminator conditioned on mu:

Why is it so? Shouldn't it be on c_code?

Why are you using gated linear units (GLU) instead of the ReLU mentioned in the paper?

Also, why did you define your own GLU instead of using the built-in one? Was there a reason or was it just not implemented yet when you wrote this?

Thanks in advance.