Comments (4)
Hi @bhanuteja2001,
it looks like the issue is coming from
GPU_threshold = 1200
The network requires a multiple of 32 as input resolution. Try setting the threshold to 1184 or 1216.
from boostingmonoculardepth.
device: cuda
Namespace(Final=True, R0=False, R20=False, colorize_results=False, data_dir='G:\Fiver\BoostingMonocularDepth\inputs', depthNet=2, max_res=inf, net_receptive_field_size=None, output_dir='G:\Fiver\BoostingMonocularDepth\output\', output_resolution=1, pix2pixsize=1024, savepatchs=0, savewholeest=0)
----------------- Options ---------------
Final: True [default: False]
R0: False
R20: False
aspect_ratio: 1.0
batch_size: 1
checkpoints_dir: ./pix2pix/checkpoints
colorize_results: False
crop_size: 672
data_dir: G:\Fiver\BoostingMonocularDepth\inputs [default: None]
dataroot: None
dataset_mode: depthmerge
depthNet: 2 [default: None]
direction: AtoB
display_winsize: 256
epoch: latest
eval: False
generatevideo: None
gpu_ids: 0
init_gain: 0.02
init_type: normal
input_nc: 2
isTrain: False [default: None]
load_iter: 0 [default: 0]
load_size: 672
max_dataset_size: 10000
max_res: inf
model: pix2pix4depth
n_layers_D: 3
name: void
ndf: 64
netD: basic
netG: unet_1024
net_receptive_field_size: None
ngf: 64
no_dropout: False
no_flip: False
norm: none
num_test: 50
num_threads: 4
output_dir: G:\Fiver\BoostingMonocularDepth\output\ [default: None]
output_nc: 1
output_resolution: None
phase: test
pix2pixsize: None
preprocess: resize_and_crop
savecrops: None
savewholeest: None
serial_batches: False
suffix:
verbose: False
----------------- End -------------------
initialize network with normal
loading the model from ./pix2pix/checkpoints/mergemodel\latest_net_G.pth
start processing
processing image 0 : sample1
wholeImage being processed in : 1792
DEBUG| GPU THRESHOLD REACHED 1792 ---> 1200
Traceback (most recent call last):
File "run.py", line 580, in
run(dataset_, option_)
File "run.py", line 125, in run
whole_estimate = doubleestimate(img, option.net_receptive_field_size, whole_image_optimal_size,
File "run.py", line 394, in doubleestimate
estimate2 = singleestimate(img, size2, net_type)
File "run.py", line 422, in singleestimate
return estimateleres(img, msize)
File "run.py", line 520, in estimateleres
prediction = leresmodel.inference(img_torch)
File "G:\Fiver\BoostingMonocularDepth\lib\multi_depth_model_woauxi.py", line 18, in inference
depth = self.depth_model(input)
File "C:\Users\Bhanu\anaconda3\envs\boost\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "G:\Fiver\BoostingMonocularDepth\lib\multi_depth_model_woauxi.py", line 32, in forward
out_logit = self.decoder_modules(lateral_out)
File "C:\Users\Bhanu\anaconda3\envs\boost\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "G:\Fiver\BoostingMonocularDepth\lib\network_auxi.py", line 57, in forward
x_8 = self.ffm2(features[2], x_16) # 1/8
File "C:\Users\Bhanu\anaconda3\envs\boost\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "G:\Fiver\BoostingMonocularDepth\lib\network_auxi.py", line 209, in forward
x = x + high_x
RuntimeError: The size of tensor a (75) must match the size of tensor b (76) at non-singleton dimension 3
from boostingmonoculardepth.
I have changed the following
whole_size_threshold = 2000 # R_max from the paper
GPU_threshold = 1200 # Limit for the GPU (NVIDIA RTX 2080), can be adjusted
from boostingmonoculardepth.
The code works fine with MiDaS.
The above error occured while using LeReS
from boostingmonoculardepth.
Related Issues (20)
- GPU thresh hold for nvidia A100 ?? HOT 2
- Code section2 error HOT 5
- Temporal inconsistency on image sequences HOT 4
- Can we use this for video input? HOT 1
- Issue max res 720 * 1280 ? HOT 8
- How to speed up the inference? HOT 2
- License of output images HOT 2
- Feature Request: Run on CPU or MPS for Apple M1/M2 HOT 4
- Unable to download mergenet model weights HOT 2
- Bit depth and banding HOT 2
- Which one of MiDas, DPT and LeRes is better for monocular depth estimation and takes the shortest time? HOT 1
- What's the parameter to be set in demo.py for "(NEW!) Now you can set the maximum resolution of the results to reduce runtime" HOT 1
- Why does NAN appear in the model inference process HOT 2
- Depth map by LeRes HOT 1
- LeRes weights download link is not working HOT 1
- How to align estimated depth with GT depth? HOT 1
- Colab error: FileNotFoundError: [Errno 2] No such file or directory: 'res101.pth' HOT 1
- Colab error: FileNotFoundError: [Errno 2] No such file or directory: './pix2pix/checkpoints/mergemodel/latest_net_G.pth' HOT 8
- no NVIDIA driver found error HOT 2
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 boostingmonoculardepth.