Train and Test R-CNN on Another Dataset #21

zeyuanxy · 2015-05-21T06:41:37Z

Hi Ross, Fast-RCNN is really fantastic! I am impressed by its great performance and speed, thus I add some other code and two READMEs to help train and test Fast-RCNN on INRIA Person, and it is easy to modify it to train on other datasets, not limiting to PASCAL VOC. It is really a honor for me to help with this, Thanks!

merged

rbgirshick · 2015-05-21T17:16:48Z

Hi @zeyuanxy, I'm curious to know what mAP you get on INRIA?

I won't be able to merge this PR in its current form because it includes the selective search code, which is under a license that does not permit redistribution.

zeyuanxy · 2015-05-21T17:32:00Z

Hi @rbgirshick It is about 87.8, a very high number.

cuatristapr · 2015-07-14T18:12:37Z

@zeyuanxy Do you have a trained model that I can already use in my project?

futurely · 2015-07-23T11:32:20Z

You don't have to stick with the MATLAB implementation of selective search. There's a pure python version.

Usage is a super easy one-liner rects = dlibss.selective_search(img, 50, 200, 3, 20, 50).

cuatristapr · 2015-07-23T20:26:03Z

How do I use it futurely? Where do I add that line to point to the python wrapper of Selective Search?

sunshineatnoon · 2015-09-14T07:19:30Z

@zeyuanxy Hi~, How did you generate images for the background class? How many images are needed for this class?

sunshineatnoon · 2015-11-15T02:33:09Z

@pradeepj247 You don't need to mention which class the image belongs to in the train.txt file, its only the names of the images, if you see classes included in images' names, that's pure coincidence. The annotation files should indicate which class a image belongs to.
For instance, a pascal voc annotation file looks like this:

<object>
        <name>dog</name>
        <pose>Left</pose>
        <truncated>1</truncated>
        <difficult>0</difficult>
        <bndbox>
            <xmin>48</xmin>
            <ymin>240</ymin>
            <xmax>195</xmax>
            <ymax>371</ymax>
        </bndbox>
    </object>

Then the name tag tells you which class this object belongs to.

Yes, you need to mention the full path to the images in factory.py.
All these three files we modified tell fast rcnn how to find data and how to parse the annotation files.

pradeepj247 · 2015-11-16T11:22:28Z

@sunshineatnoon, just 2 more questions:

I) in your Factory.py, there are 3 for..loops outside the functions, and they contain, the imagenet_devkit_path = '/home/xuetingli/imagenet' and towncenter_devkit_path = '/home/szy/TownCenter' and also inria_devkit_path = '/home/xuetingli/test/INRIA'. This is a bit confusing for me. if you are dealing with only one dataset (i.e imagenet), then only the imagenet should suffice?

after setting up everything as mentioned by you and when I run train, i see this error:
EnvironmentError: MATLAB command 'matlab' not found. Please add 'matlab' to your PATH.
do we still need MATLAB? I thought this was a pure Python implementation, especially, if we bring in our own selective search proposals and train.mat

sunshineatnoon · 2015-11-16T11:46:44Z

yes, only imagenet loop is needed, you can deleted others. As I mentioned, I referred here for how to modify the code, so I didn't delete what the author wrote initially.
this error is caused by code in lib/datasets/init.py, so just comment it out:

if _which(MATLAB) is None:
    msg = ("MATLAB command '{}' not found. "
           "Please add '{}' to your PATH.").format(MATLAB, MATLAB)
    raise EnvironmentError(msg)'''

pradeepj247 · 2015-11-17T07:59:31Z

Thanks @sunshineatnoon,

I crossed all those stages - it loaded the dataset, annotations and the caffeNet model required for training.

But just before starting the training, it failed with the following error:
Check failed: error == cudaSuccess (8 vs. 0) invalid device

This seems to be quite a popular error and I read quite a few posts on the forums, but couldn't resolve it.

I am running this on AWS g2.2x and my caffe device_query call works fine.

Any suggestions on how to get past this one?

KrasusC · 2015-12-24T17:56:22Z

@DaChaoXc I met the problem you mentioned. Have you figured it out?

leejiajun · 2016-01-13T08:53:48Z

@DaChaoXc
@KrasusC
@nicci1771
I met the problem you mentioned. Have you figured it out?
"./tools/train_net.py", line 80, in
roidb = get_training_roidb(imdb)
File "/home/xc/fast-rcnn-master/tools/../lib/fast_rcnn/train.py", line 107, in get_training_roidb
imdb.append_flipped_images()
File "/home/xc/fast-rcnn-master/tools/../lib/datasets/imdb.py", line 99, in append_flipped_images
boxes = self.roidb[i]['boxes'].copy()
File "/home/xc/fast-rcnn-master/tools/../lib/datasets/imdb.py", line 63, in roidb
self._roidb = self.roidb_handler()
File "/home/xc/fast-rcnn-master/tools/../lib/datasets/inria.py", line 116, in selective_search_roidb
ss_roidb = self._load_selective_search_roidb(gt_roidb)
File "/home/xc/fast-rcnn-master/tools/../lib/datasets/inria.py", line 138, in _load_selective_search_roidb
return self.create_roidb_from_box_list(box_list, gt_roidb)
File "/home/xc/fast-rcnn-master/tools/../lib/datasets/imdb.py", line 167, in create_roidb_from_box_list
argmaxes = gt_overlaps.argmax(axis=1)
ValueError: attempt to get argmax of an empty sequence

nwestlake · 2016-01-13T15:09:32Z

@leejiajun
Try applying the changes proposed here: #102

e.g.
git fetch git@github.com:nw362/fast-rcnn.git negativeImages:negativeImages
git merge negativeImages

(I am interesting in the pull request too, so I might later try merging it with mine.)

leejiajun · 2016-01-14T03:05:31Z

@nw362
nice work! I will fetch you code, thank you.

aragon111 · 2016-04-01T16:56:54Z

Hello,
when I try to train, I get this error

File "/home/attilio/fast-rcnn/tools/../lib/datasets/amph.py", line 190, in get_data_from_tag
return node.getElementsByTagName(tag)[0].childNodes[0].data
IndexError: list index out of range

Would you help to understand how to fix it?
I don't know if it depends on the Annotation file I have or some editing error of python files (I use just one class)

nwestlake · 2016-04-01T19:59:05Z

This looks to be code you have written (amph.py)? Hard to say without seeing both the code and the annotation file.

aragon111 · 2016-04-02T15:20:12Z

I fixed it adding to the .xml files (which I got from Matlab) the fields name and folder.

MinaRe · 2016-04-19T09:35:28Z

Dear All, (@zeyuanxy )
can you please kindly tell me how can I change batch_size?

IdiosyncraticDragon · 2016-04-19T09:52:25Z

Editing the config file FAST-RCNN-ROOT/lib/fast_rcnn/config.py

发自我的 iPhone

在 2016年4月19日，下午5:35，MinaRe notifications@github.com 写道：

Dear All,
can you please kindly tell me how can I change batch_size?

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub

MinaRe · 2016-04-19T12:11:48Z

thanks @IdiosyncraticDragon
Actually my training stop during "Computing bounding-box regression targets..." ,do you have any Idea? is this problem because of memory size? I have 50k images, How much CPU memory do I need for training?

IdiosyncraticDragon · 2016-04-19T12:42:14Z

Well, that's because of too much training data. I don't know whether it will be helpful if you have more memory size.

发自我的 iPhone

在 2016年4月19日，下午8:11，MinaRe notifications@github.com 写道：

thanks @IdiosyncraticDragon
Actually my training stop during "Computing bounding-box regression targets..." ,do you have any Idea? is this problem because of memory size?

—
You are receiving this because you were mentioned.
Reply to this email directly or view it on GitHub

aragon111 · 2016-04-25T14:25:45Z

Can you tell me why running detection, the frame detect just one item at a time?

nwestlake · 2016-04-25T14:48:12Z

One ROI at a time?

aragon111 · 2016-04-25T14:49:49Z

@nw362 exactly :)

nwestlake · 2016-04-25T14:52:21Z

The convolutional layers of the CNN are calculated on the whole image (resized before hand). The final polling layer pools over only the ROI and so the CNN must run the forward steps over these layers for every ROI.

aragon111 · 2016-04-25T14:56:07Z

In order to detect more ROIs in the same frame there is anything I could do?

nwestlake · 2016-04-25T15:04:13Z

It should happen already "lib/fast_rcnn/test.py": _get_blobs will take in one image but multiple ROIs. In im_detect(net, im, boxes), the CNN will be called forward only once for an image and a set of ROIs. Is only one ROI being sent to this method?

aragon111 · 2016-04-25T15:20:20Z

@nw362 I checked and it seems to me that it does not send only one ROI.

aragon111 · 2016-05-09T07:52:21Z

I have a little doubt. During the labeling of the training set, is it possible to label more items (ROIs) in the same image?

nwestlake · 2016-05-09T11:48:27Z

Yes, e.g. the xml format used for annotations.

aragon111 · 2016-05-09T12:41:15Z

@nw362 Do you mean that is not a problem if there are more bounding boxes for the same .xml file?

nwestlake · 2016-05-09T12:43:19Z

No problem at all. This is the case for many data sets.

aragon111 · 2016-05-09T12:47:49Z

@nw362 I'm not sure about what you mean with many data sets. I have only two classes (background and amphora) and in some image from the data set there are many amphoras.

mksarker · 2016-07-11T07:32:25Z

hi all,
I have followed the below web instruction for training my own dataset as INRIA,
https://github.com/zeyuanxy/fast-rcnn/blob/master/help/train/README.md
and found the below problem,
:$ cd fast-rcnn
:/fast-rcnn$ ./tools/train_net.py --gpu 0 --solver models/pascal_voc/VGG_CNN_M_1024/fast-rcnn/solver.prototxt --weights data/faster_rcnn_models/VGG16_faster_rcnn_final.caffemodel --imdb inria_train
/home/sarker/anaconda2/lib/python2.7/site-packages/matplotlib/font_manager.py:273: UserWarning: Matplotlib is building the font cache using fc-list. This may take a moment.
warnings.warn('Matplotlib is building the font cache using fc-list. This may take a moment.')
Python 2.7.11 |Anaconda custom (64-bit)| (default, Jun 15 2016, 15:21:30)
Type "copyright", "credits" or "license" for more information.

IPython 4.2.0 -- An enhanced Interactive Python.
? -> Introduction and overview of IPython's features.
%quickref -> Quick reference.
help -> Python's own help system.
object? -> Details about 'object', use 'object??' for extra details.

In [1]:

when I run the training code on terminal the IPython console is open? I don’t know what is the problem? I am a beginner in this area. Please help me.
Thanks in advanced....

zeyuanxy added 22 commits May 7, 2015 14:09

initialize

91fe412

Merge branch 'master' of https://github.com/EdisonResearch/fast-rcnn

24edaef

merged

refine

11ee13a

add raw framework for training INRIA

4b2c22e

a simple setup

57d43ea

need to parse annotations of INRIA

ae56151

it seems that the annotations work well

a74a217

add selective search

288e28a

start training on INRIA!

fb9cf91

modify prototxt

7de785d

update prototxt

ba4b768

minor fix

8b77098

start testing

51e257d

start writing readme

34c69d6

test on TownCenter

d363a31

minor fix

4087705

add selective search

9d72bc0

add How to Train

eb54f54

update train.md

48ddd80

add VOCcode

1be5807

update train.md

89bea59

add test.md

33367c0

zeyuanxy added 2 commits May 22, 2015 12:56

fix in models of training

6db56f5

minor fix

1084f3e

Zeyuan Shang added 2 commits April 11, 2016 10:39

update README.md

9ff516a

update README.md

2e41f4e

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Train and Test R-CNN on Another Dataset #21

Train and Test R-CNN on Another Dataset #21

zeyuanxy commented May 21, 2015

rbgirshick commented May 21, 2015

zeyuanxy commented May 21, 2015

cuatristapr commented Jul 14, 2015

futurely commented Jul 23, 2015

cuatristapr commented Jul 23, 2015

sunshineatnoon commented Sep 14, 2015

sunshineatnoon commented Nov 15, 2015

pradeepj247 commented Nov 16, 2015

sunshineatnoon commented Nov 16, 2015

pradeepj247 commented Nov 17, 2015

KrasusC commented Dec 24, 2015

leejiajun commented Jan 13, 2016

nwestlake commented Jan 13, 2016

leejiajun commented Jan 14, 2016

aragon111 commented Apr 1, 2016

nwestlake commented Apr 1, 2016

aragon111 commented Apr 2, 2016

MinaRe commented Apr 19, 2016 •

edited

IdiosyncraticDragon commented Apr 19, 2016

MinaRe commented Apr 19, 2016 •

edited

IdiosyncraticDragon commented Apr 19, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016 •

edited

aragon111 commented May 9, 2016 •

edited

nwestlake commented May 9, 2016

aragon111 commented May 9, 2016

nwestlake commented May 9, 2016

aragon111 commented May 9, 2016

mksarker commented Jul 11, 2016

Train and Test R-CNN on Another Dataset #21

Are you sure you want to change the base?

Train and Test R-CNN on Another Dataset #21

Conversation

zeyuanxy commented May 21, 2015

rbgirshick commented May 21, 2015

zeyuanxy commented May 21, 2015

cuatristapr commented Jul 14, 2015

futurely commented Jul 23, 2015

cuatristapr commented Jul 23, 2015

sunshineatnoon commented Sep 14, 2015

sunshineatnoon commented Nov 15, 2015

pradeepj247 commented Nov 16, 2015

sunshineatnoon commented Nov 16, 2015

pradeepj247 commented Nov 17, 2015

KrasusC commented Dec 24, 2015

leejiajun commented Jan 13, 2016

nwestlake commented Jan 13, 2016

leejiajun commented Jan 14, 2016

aragon111 commented Apr 1, 2016

nwestlake commented Apr 1, 2016

aragon111 commented Apr 2, 2016

MinaRe commented Apr 19, 2016 • edited

IdiosyncraticDragon commented Apr 19, 2016

MinaRe commented Apr 19, 2016 • edited

IdiosyncraticDragon commented Apr 19, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016

nwestlake commented Apr 25, 2016

aragon111 commented Apr 25, 2016 • edited

aragon111 commented May 9, 2016 • edited

nwestlake commented May 9, 2016

aragon111 commented May 9, 2016

nwestlake commented May 9, 2016

aragon111 commented May 9, 2016

mksarker commented Jul 11, 2016

MinaRe commented Apr 19, 2016 •

edited

MinaRe commented Apr 19, 2016 •

edited

aragon111 commented Apr 25, 2016 •

edited

aragon111 commented May 9, 2016 •

edited