Comments (7)
yassouali
commented on September 12, 2024
Hi, I guess you only need to add the mode (fine or coarse) make sure you use bigger base and crop sizes given the size of the CS images; here is an example:
"train_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 8,
"base_size": 1024,
"crop_size": 512,
"augment": true,
"shuffle": true,
"scale": true,
"flip": true,
"rotate": true,
"blur": false,
"split": "train",
"mode": "fine",
"num_workers": 8
}
},
"val_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 1,
"val": true,
"split": "val",
"mode": "fine",
"num_workers": 4
}
}from pytorch-segmentation.
edizhuang
commented on September 12, 2024
Hi Yassine,
Thanks for the quick reply. I see the original image size is 2018 * 1024, so here what's the input size and patch size for training? For validation are you using the original size?
from pytorch-segmentation.
edizhuang
commented on September 12, 2024
Hi Yassine,
Thanks for the quick reply. I see the original image size is 2018 * 1024, so here what's the input size and patch size for training? For validation are you using the original size?
Best,
Chengyuan
…________________________________
From: Yassine <[email protected]>
Sent: Tuesday, October 22, 2019 12:03
To: yassouali/pytorch_segmentation <[email protected]>
Cc: edizhuang <[email protected]>; Author <[email protected]>
Subject: Re: [yassouali/pytorch_segmentation] Config file for CityScapes (#14)
Hi, I guess you only need to add the mode (fine or coarse) make sure you use bigger base and crop sizes given the size of the CS images; here is an example:
"train_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 8,
"base_size": 1024,
"crop_size": 512,
"augment": true,
"shuffle": true,
"scale": true,
"flip": true,
"rotate": true,
"blur": false,
"split": "train",
"mode": "fine",
"num_workers": 8
}
},
"val_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 1,
"val": true,
"split": "val",
"mode": "fine",
"num_workers": 4
}
}
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#14>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ADZSWLDZZLNHQHLC422BADLQP4W4RANCNFSM4JDSENYQ>.
from pytorch-segmentation.
yassouali
commented on September 12, 2024
First step is to resize the bigger size to 1024 (so 1024 x 512) then a scaling then a random crop of 512 x 512, for validation you can either take crops of 1024 with a bigger batch for quick processing, or use the original size with a batch of 1, accurate but slow.
from pytorch-segmentation.
edizhuang
commented on September 12, 2024
Thanks!
from pytorch-segmentation.
edizhuang
commented on September 12, 2024
Thanks!
By the way, I got this error when using 4 GPUs: ValueError: Caught ValueError in replica 3 on device 3.
Use one GPU is OK.
File "train.py", line 61, in <module>
main(config, args.resume)
File "train.py", line 42, in main
trainer.train()
File "/storage/scratch2/cz0056/city/yassouali-deeplab/base/base_trainer.py", line 98, in train
results = self._train_epoch(epoch)
File "/storage/scratch2/cz0056/city/yassouali-deeplab/trainer.py", line 56, in _train_epoch
output = self.model(data)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 152, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 162, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 85, in parallel_apply
output.reraise()
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/_utils.py", line 369, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in replica 3 on device 3.
Original Traceback (most recent call last):
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 60, in _worker
output = module(*input, **kwargs)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/storage/scratch2/cz0056/city/yassouali-deeplab/models/deeplabv3_plus.py", line 357, in forward
x = self.ASSP(x)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/storage/scratch2/cz0056/city/yassouali-deeplab/models/deeplabv3_plus.py", line 291, in forward
x5 = F.interpolate(self.avg_pool(x), size=(x.size(2), x.size(3)), mode='bilinear', align_corners=True)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/container.py", line 92, in forward
input = module(input)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 81, in forward
exponential_average_factor, self.eps)
File "/cm/shared/utils/PYTHON/pytorch-gpu1.2.0/lib/python3.6/site-packages/torch/nn/functional.py", line 1652, in batch_norm
raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])
…________________________________
From: Yassine <[email protected]>
Sent: Tuesday, October 22, 2019 12:03
To: yassouali/pytorch_segmentation <[email protected]>
Cc: edizhuang <[email protected]>; Author <[email protected]>
Subject: Re: [yassouali/pytorch_segmentation] Config file for CityScapes (#14)
Hi, I guess you only need to add the mode (fine or coarse) make sure you use bigger base and crop sizes given the size of the CS images; here is an example:
"train_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 8,
"base_size": 1024,
"crop_size": 512,
"augment": true,
"shuffle": true,
"scale": true,
"flip": true,
"rotate": true,
"blur": false,
"split": "train",
"mode": "fine",
"num_workers": 8
}
},
"val_loader": {
"type": "CityScapes",
"args":{
"data_dir": "/data/Cityscapes",
"batch_size": 1,
"val": true,
"split": "val",
"mode": "fine",
"num_workers": 4
}
}
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#14>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/ADZSWLDZZLNHQHLC422BADLQP4W4RANCNFSM4JDSENYQ>.
from pytorch-segmentation.
yassouali
commented on September 12, 2024
With 4 GPUs, maybe the batch size is say 7, in this case each GPU will have 2 Images but the last one with one image, and his will give you an error, try a batch size = GPUs * 2 at least.
from pytorch-segmentation.
Related Issues (20)
- resume training problem HOT 1
- How to use the pretrained model to output one class HOT 1
- Using Unet for training in Freiburg Forest dataset HOT 1
- LOSS is shown as Nan. HOT 2
- Binary segmentation on a custom dataset HOT 1
- How to set the "weight" for CrossEntropyLoss2d in config file? HOT 1
- RuntimeError: cuda runtime error (11) : invalid argument at /pytorch/aten/src/THC/THCGeneral.cpp:383 HOT 1
- Resnet model URLs inaccessible HOT 1
- I have some environment problem.
- what is ADE20K configfile ? HOT 1
- hi，can you tell me if I want to train segnet，should I download vgg or other backbone?
- Test evaluation with custom Dataset HOT 1
- UNet decoder layers double conv might have logical errors HOT 1
- Issues with JSON parser in the train.py file.
- How to activate GPU training? HOT 2
- No Output on cityscape dataset
- URL broken for ResNet50, 101, 152 HOT 1
- RailSem19 Dataset
- FCN model can't restore the image to its original resolution
- Deeplab V3+ model doesn't support ResNet-50 as backbone?
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 pytorch-segmentation.