search

layumi / Image-Text-Embedding

TOMM2020 Dual-Path Convolutional Image-Text Embedding :feet: https://arxiv.org/abs/1711.05535
MIT License
287 stars 73 forks source link

The loss on COCO dataset of training stage1 dosen't decrease #5

Open BruceW91 opened 6 years ago

BruceW91 commented 6 years ago

Hi, I run the train_coco_word2_1_pool.m, but after more than 10 epochs, I found the train result is still bad(as below). I didn't change any hyper parameters but I don't know why it doesn't work. qq 20180515115715 Can you tell me what make this result happen? And I found the learning rate in your code is 0.1, but it's reported as 0.001 in the paper. Which lr is correct and better in this task?

layumi commented 6 years ago

The learning rate = global learning rate * layer learning rate. For COCO, it may converge slowly. It may take about 20 epochs to start converging.

layumi commented 6 years ago

I also notice there is error in your code? @habbakuk1103 Do you prepare the dataset in the right way?

BruceW91 commented 6 years ago

Thank you for response. I think I prepare the COCO dataset as you told, but the dimension of my 'coco_dictionary.mat' is 29141, but it's 29972 in your code. I don't know whether it's caused by I prepare the dataset in the matlab r2016b on Windows system of my computer because I can't install this version on our linux server. Could you give me a link to download the data after preprocessed as below if possible? qq 20180515202323 By the way, I am not familiar with matconvnet. Could you tell me what the 'error' in the result mean? I check the code before and I think the data and label should be aligned.

layumi commented 6 years ago

image

I wonder whether you provided the right file path.

BruceW91 commented 6 years ago

The path of the 'prepare_imdb.m' is as below in matlab on my server, but its version is matlab R2014b which doesn't have 'jsondecode' function 1 So I implement the program on my computer, thus the path is changed as below 2 I wonder whether this difference of paths cause the problem.

BruceW91 commented 6 years ago

I have solved the problem. Thank you for your suggestion.