File "main_IRT.py", line 7, in import tensorflow as tf ModuleNotFoundError: No module named 'tensorflow' Traceback (most recent call last): File "main_IRT.py", line 7, in import tensorflow as tf ModuleNotFoundError: No module named 'tensorflow' Traceback (most recent call last): File "main_IRT.py", line 7, in import tensorflow as tf ModuleNotFoundError: No module named 'tensorflow' Traceback (most recent call last): File "main_IRT.py", line 7, in import tensorflow as tf ModuleNotFoundError: No module named 'tensorflow'

上面是计算出来的图片，具体命令如下： python main_IRT.py --max_epoch 50 --input demo/colorization/ai_input1000 --processed demo/colorization/ai_processed1000 --model enhancement --with_IRT 1 --IRT_initialization 1 --output ./result/colorization1000/ 表现效果为：第三张图片偏黄，且受到了之前帧炮弹爆炸画面黄光的影响。

同样的model colorization参数也试过，表现效果为：图片直接变成了晚上，深蓝色的天空，与实际上色图片差距太大。

小弟才学有限，对大佬十分敬仰，期待您的解答。

HI, I am trying to process a large video (10 min) to deflicker after colorization. I have left my system on to run for about 24 hours after witch it trained for 50 epochs. After 50 epochs the result is still quite poor and looks more like the original black and white video than the colorized one. Did you ever test on longer video’s? Is the result going to improve with more training epochs? Or is it impossible to use your model on a video this long? Thanks in advance for your answer!

Traceback (most recent call last): File "dvp_video_consistency.py", line 6, in import scipy.io ModuleNotFoundError: No module named 'scipy'

Thanks for your excellent work!

I have two questions about the Deep Video Prior.

1、Have you attempted to do some experiments about VSR with the deep video prior? if yes, how about the performance?

2、In my opinion, the temporal consistency of output frames highly depends on the temporal consistency of input frames. If the input frames don't have good temporal consistency, can this deep video prior work?

Hope you can help me solve above problem.

After running supplied demo (regardless of used task ) resolution of output video frames is different from than resolution of input/processed frames. e.g. resolution of "goat_input and goat_processed" frames is 854x480 however output result is 832x480. Processing my own frames (regardless of used task) with 1440x1080 delivers frames with 1440x1056.

When attempting to run main_IRT.py with 6000 frames causes RuntimeError: CUDA out of memory. This could be fixed by reducing batch size or use memory when needed. Also, I`m using google Colab and yes the ram that google collab had offered did not reach the full amount of ram instead, it stopped at 2/3 of it and caused this error

Traceback (most recent call last): File "main_IRT.py", line 139, in net_in = torch.from_numpy(net_in).permute(0,3,1,2).float().to(device) RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 14.73 GiB total capacity; 12.13 GiB already allocated; 5.88 MiB free; 13.79 GiB reserved in total by PyTorch)

我做了一个戴口罩的视频修改功能，videoFrames文件夹下是视频拆帧数据，processed/colorization文件夹下是戴面具处理的数据，两文件夹各6000张图片(1920*720)，使用的是： python main_IRT.py --max_epoch 1 --input videoFrames --processed processed/colorization --model colorization --with_IRT 1 --IRT_initialization 1 --output ./result/colorization/AddMask 我的CPU直接干到100%， 内存128也不够用，电脑就卡住了，具体配置如下： "--use_gpu", default=1, tensorflow-gpu=1.13.1

期待您的解答，感谢您！

Hi, thanks a lot for your amazing work. I wonder whether you could share your code to calculate Ewarp, which is mentioned in your paper to evaluate temporal consistency. Thanks a lot.

Dear author, I tried to implement the code for learning, however, an error appeared when I compiled the command [ python download_VGG.py ], which points to that the url of downloading VGG.zip is invalid now. Therefore, if convenient, could you please show me another one?

Hi, First all, thank you for your good work ! We have one question: Final video flickering a little more using you source code. Video source is under your demo/spatial_white_balance. Attach is test result. video.zip Would you like give us some suggestion ? Many thanks.

Hey I was creating a colab notebook for your code but I am facing some issues a lot of requirements are missing can you please create a colab notebook? Please

Upon running "main_IRT.py", got an error:

Exception has occurred: ValueError
attempt to get argmax of an empty sequence
  File "D:\colorization\deep-video-prior-master-pytorch\main_IRT.py", line 49, in <module>
    for x in subprocess.Popen("nvidia-smi -q -d Memory | grep -A4 GPU | grep Free", shell=True, stdout=subprocess.PIPE).stdout.readlines()]))

Happened in both Windows 10 and WSL2 Nvidia RTX 3090