Caffe-LMDBCreation-MultiLabel

Caffe-LMDBCreation-MultiLabel copied to clipboard

not able to generate lmdb

5

i gave path to each and every variable in create_data_lmdb.sh ``` EXAMPLE=/home/kush/Desktop/Caffe_project/lmdbs # Path where the output LMDB is stored DATA=/home/kush/Desktop/Caffe_project/ # Path where the data.txt file is present TOOLS=/home/kush/caffe/tools...

kushNumberTheory

why label sholud be [0 255]

5

I have 4 classes and assign 0 0 1 1 to it ， and in train.prototxt label data not have the param scale , I think this is ok? why...

zack6514

load weights from a pre-trained Caffe model

4

Hi, First of all thank you for your contributions, your code has been very helpful. I've managed to run my model from the scratch. I was wondering if it is...

k-eak

Mirror should not exist in Train Data layer. Or should also exist in Train Label layer.

1

https://github.com/sukritshankar/Caffe-LMDBCreation-MultiLabel/blob/f4a92fcf4282ea808cd3c6bb5ade2712e23d2dbf/train_vgg_11_sigmoid_cross_entropy_loss.prototxt#L17

aniket03

Database environment version mismatch

1

Hello, Thank you for the great work. I am trying to train a net for multi label image classification, however when I use caffee to do so, I run into...

vbvxx

Thank you for your contribution! Now ，I want to use it for 256 dimensional labels classification. Each label is 0 or 1. But the loss of training is strange. It...

Chenly1993

Finetune model with wrong loss

1

Hi, Thanks for your contributions.I have dataset with 171 classes like closed issue #1 ,for example（image01.jpg 2 167 45）.And I'd like to finetune with vgg16. I modifity train_val.prototxt like yours.I...

StOnEGiggity

LMDB multidim labels

4

I created train and test datasets with each entry looking like: /Data/train/00001.png 347.0 178.0 408.0 283.0 where the four digits are bounding box values (x,y,h,w) of a bounding box. The...

AlexTS1980

label lmdb not right

9

when i created lmdb follow the code ,i get the error : inner_num_ == bottom[1]->count() (1 vs. 20) Number of labels must match number of predictions; 20 is the number...

yayong-guan