hi, While running for split 10 classification on SHREC do we need to change the ba

Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

classification SHREC for split 10 about meshcnn HOT 2 CLOSED

ranahanocka commented on May 19, 2024

classification SHREC for split 10

from meshcnn.

Comments (2)

ranahanocka commented on May 19, 2024 1

Hi @kamran-afzal ,

We followed the setup described in (GWCNN)[https://people.csail.mit.edu/jsolomon/assets/GW_for_CNN.pdf] (see Table 1). Shrec10 vs. Shrec16 is the train / test split. Where Shrec16 is 16 examples in the train and 4 in the test, and Shrec10 was 10 / 10. The batch size and all the other settings we used were the same for shrec16 and shrec10. You can just run the code as show here :

MeshCNN/scripts/shrec/train.sh

Lines 3 to 14 in 29c30a4

 ## run the training 

 python train.py \ 

 --dataroot datasets/shrec_16 \ 

 --name shrec16 \ 

 --ncf 64 128 256 256 \ 

 --pool_res 600 450 300 180 \ 

 --norm group \ 

 --resblocks 1 \ 

 --flip_edges 0.2 \ 

 --slide_verts 0.2 \ 

 --num_aug 20 \ 

 --niter_decay 100 \

from meshcnn.

kamran-afzal commented on May 19, 2024

thanks for your kind reply.

from meshcnn.

classification SHREC for split 10 about meshcnn HOT 2 CLOSED

Comments (2)

Related Issues (20)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

	## run the training
	python train.py \
	--dataroot datasets/shrec_16 \
	--name shrec16 \
	--ncf 64 128 256 256 \
	--pool_res 600 450 300 180 \
	--norm group \
	--resblocks 1 \
	--flip_edges 0.2 \
	--slide_verts 0.2 \
	--num_aug 20 \
	--niter_decay 100 \