Training data list for Cityscapes about tusimple-duc HOT 12 CLOSED

Maybe you should read the code more carefully, we assign different anchors in the data_prep/get_cityscapes_list.py:

for i in range(1, 8):
    train_lst.append([str(index), p, l, "512", str(256 * i)])

And together with TuSimple-DUC/tusimple_duc/core/utils.py

def get_single_image_duc(item, input_args):

That's exactly how we do data augmentation.

from tusimple-duc.

@chienyiwang fix by #7

from tusimple-duc.

see #2.

from tusimple-duc.

Hi @GrassSunFlower Thanks for the reply. However, the list only provides the image/annotation filename in each line. Would you be able to provide the download link of actual augmented training data for easier training? Thank you!

from tusimple-duc.

Hi @GrassSunFlower, I see. Sorry I presumed you are extracting 35700 images into a separate folder which follows the usual segmentation data pipeline. Thanks for the explanation!

from tusimple-duc.

Hi @GrassSunFlower , could I ask some questions related to the gen_cityscapes_list.py code?

1. What is the usage of the following code segment
   if index % sample_rate != 2: continue
2. What is the reason for printing out the same line twice (from line 28-30)?

for line in train_lst:
        print >> train_out, '\t'.join(line)
        print >> train_out, '\t'.join(line)

Thank you very much!

from tusimple-duc.

These two statements should be two bugs.
Thanks for your patience. I'll fix them shortly.

from tusimple-duc.

Hi，@chienyiwang
Have you trained the model on the Cityscapes?
what's the performance your trained model on the val dataset?

from tusimple-duc.

Hi ,@GrassSunFlower @wpqmanu Is there a error in data_prep/get_cityscapes_list.py. the train lst has only 20825 lines, not 35700. because of range(1,8) = [1,2,3,4,5,6,7]

from tusimple-duc.

Nope.
35700 should came from our paper saying that

 Since the image size in the Cityscapes dataset
is 1024 × 2048, which is too big to fit in the GPU memory,
we partition each image into twelve 800×800 patches with
partial overlapping, thus augmenting the training set to have
35700 images.``` which is in the 'baseline model'.

And our actual augmentation utilized is in 'Bigger Patch Size', which says

 Since the patch size
exceeds the maximum dimension (800 × 800) in the previous
12-fold data augmentation framework, we adopt a new
7-fold data augmentation strategy: seven center locations
with x = 512, y = {256, 512, ..., 1792} are set in the original
image;

which is 7*2975.
Hope this will help you out. @shipeng-uestc

from tusimple-duc.

@GrassSunFlower Thanks for your reply. I figure out it.
I have another question. Can I use directly init.param to train on cityscape fine annotation dataset and need not to change super-paramter i.e. batch_size learning rate and so on.

from tusimple-duc.

Sure you do.

from tusimple-duc.