can't test "High Quality Segmentation for Ultra High-resolution Images" #21
Comments
|
I suggest you insert PDB or Print before line 138 of dataset/offline_dataset_crm_pad32.py to see if you can load the image manually. Thanks. |
I loaded img variable by image file.png but in seg variable, dataset miss "_seg.png" file |
|
So, if you don't want to modify the dataset code, please change your dataset form. Or keep your dataset, and modify the code for loading seg.png. Thanks. |
Thank you for your answer, What is the meaning of seg variable and "_seg.png" image, i want to modify the code for generate seg variable to produce "coord" variable and "cell "varibale |
|
|
|
Hi, have you run through the ENTITY coarse partition network yet? I am getting the following error when running this coarse partition network with instances2017 dataset： ERROR [08/05 15:18:06 d2.engine.train_loop]: Exception during training: |
I've seen it a lot in some issues, but I don't know what it is meaning of detectron2-main ?, what does it do? |
|
This is the download of detectron2 according to the readme of the entity network |
I think this repo has 2 projects. one is entity, the other is High-Quality-Segmention. Which one are you working with? .Im working with High-Quality-Segmention |
|
Im working with entity,The first picture shows the readme file of the entity network. Which one has you worked with? |
|
“High Quality Segmentation for Ultra High-resolution Images” doesn't need detectron2. Thanks. |
|
I got it, Thanks
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年8月11日(星期四) 下午4:53
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [dvlab-research/Entity] can't test "High Quality Segmentation for Ultra High-resolution Images" (Issue #21)
“High Quality Segmentation for Ultra High-resolution Images” doesn't need detectron2. Thanks.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
So, what's your problem? The coarse mask from segmentation model is needed. Thanks. |
|
I used the coarse mask from pspnet
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年8月11日(星期四) 下午4:55
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [dvlab-research/Entity] can't test "High Quality Segmentation for Ultra High-resolution Images" (Issue #21)
I try to test by using model_10000 and take seg by gray image but the result is so weird seg = Image.open(im[:-4]+'.png').convert('L') seg = self.resize_bi(crop_lambda(Image.open(im).convert('L')))
So, what's your problem? The coarse mask from segmentation model is needed. Thanks.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
I understood seg.png as raw mask of another segmentation neural network . So "High Quality Segmentation for Ultra High Resolution Images" is a post-processing right? |
|
yean!
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2022年8月11日(星期四) 下午5:01
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [dvlab-research/Entity] can't test "High Quality Segmentation for Ultra High-resolution Images" (Issue #21)
coarse mask
I understood seg.png as raw mask of another segmentation neural network . So "High Quality Segmentation for Ultra High Resolution Images" is a post-processing right?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
I run test.py but i met this error, miss "_seg.png" file
python test.py --dir ./data/DUTS-TE --model ./model_10000 --output ./output --clear
/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torchvision/io/image.py:11: UserWarning: Failed to load image Python extension: /home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torchvision/image.so: undefined symbol: _ZNK2at10TensorBase21__dispatch_contiguousEN3c1012MemoryFormatE
warn(f"Failed to load image Python extension: {e}")
before_Parser_time: 1659253874.6776164
Hyperparameters: {'dir': './data/DUTS-TE', 'model': './model_10000', 'output': './output', 'global_only': False, 'L': 900, 'stride': 450, 'clear': True, 'ade': False}
ASPP_4level
12 images found
before_for_time: 1659253881.0989463 ; before_for_time - before_Parser_time: 6.421329975128174
Traceback (most recent call last):
File "test.py", line 106, in
for im, seg, gt, name, crm_data in progressbar.progressbar(val_loader):
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/progressbar/shortcuts.py", line 10, in progressbar
for result in progressbar(iterator):
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/progressbar/bar.py", line 547, in next
value = next(self._iterable)
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/hoang/Desktop/luanvan/implicitmodel/4cham/Entity/High-Quality-Segmention/dataset/offline_dataset_crm_pad32.py", line 138, in getitem
im, seg, gt = self.load_tuple(self.im_list[idx])
File "/home/hoang/Desktop/luanvan/implicitmodel/4cham/Entity/High-Quality-Segmention/dataset/offline_dataset_crm_pad32.py", line 110, in load_tuple
seg = Image.open(im[:-7]+'_seg.png').convert('L')
File "/home/hoang/anaconda3/envs/tranSOD/lib/python3.6/site-packages/PIL/Image.py", line 2975, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: './data/DUTS-TE/sun_abzsyxfgntlvd_seg.png'
The text was updated successfully, but these errors were encountered: