Can you please upload the pretrained model.?

please kindly tell me how to solve this problem ,which happening when i run the main.py .thank you very much
FileNotFoundError: [Errno 2] No such file or directory: 'sample.npz'
@GitBoSun

Hi!

The link[http://lsun.cs.princeton.edu/challenge/2015/roomlayout/data/training.mat]and [http://lsun.cs.princeton.edu/challenge/2015/roomlayout/data/validation.mat]are invalid.When I searched for this link,the page displays "The requested URL was not found on this server." Can you upload mat files to github?

Thank you very much!

Hi, thank you for the code. I followed your instructions and managed to train a model using the vanilla network. However, my test results are not correct. The room classification label is mostly correct, but the layout is almost always wrong. See the examples below...


See my training loss curves below. The classification loss goes down to almost zero but the layout loss is still quite high. Do you know why this might be?

I get this error of file missing "out=np.load('rcnn/test/2.npz')"
Kindly guide me how to overcome this.
Regards

File "/home/ahmad/anaconda3/lib/python3.6/site-packages/numpy/lib/npyio.py", line 372, in load
fid = open(file, "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'rcnn/test/2.npz'

Hi, I tried to run your pre-trained model with my own images, but I don't imagine how to do that. Can you give me maybe some instructions or tips?

Sir, Can you please upload the link of LSUN dataset which you use in your code.

I've been working implementation of RoomNet with your code, but i found there is a few bugs and it still doesn't make a satisfied result. I think there must be a few more bugs that should be modified, but I can't figure it out at all.

Can you please share the code working well??????

Hi, Could you please reshare the sample.npz file ?

In this part:
New: You can find pre-trained model here and sample.npz for get_res.py here

when I click on (Here) I get ERROR 404

Thank you so much

here are the results of some pictures

In
get_res.py file
out np.load(sample.npz)
Can you please tell me how to take this
sample.npz
Either I need to download or need to prepare like other .npz files using prepare_data.py

How much time it needs to train the network usually on normal core i5 computer.?

regards

i am able to train the model using RCNN and vanilla.

1. while training and validation, the script uses .mat files to get the image information. But i dont have any clue which information it contains and can we generate .mat file for own images? if so, which parameters I need to consider the to save in MAT file.

2. After training, How can I run inference on single image or set of images?

please help me out, Thanks

Hi!
I have a problem with reproducibility of the predictions on inference. Below I attached the code I use to make predictions on samples from the file you provided: sample.npz.

I made one more function in addition to yours train and test for inference:

def inference(args):
    out_path = Path(args.out_path)

    outdir = out_path / 'inference'
    model_dir = out_path / 'model'

    if not outdir.exists():
        os.makedirs(outdir)

    config = tf.ConfigProto()
    config.gpu_options.allow_growth = True
    config.allow_soft_placement = True

    sess = tf.Session(config=config)
    device = '/gpu:0'
    if args.gpu == 1:
        device = '/gpu:1'
    with tf.device(device):
        if args.net == 'vanilla':
            net = RoomnetVanilla()
        if args.net == 'rcnn':
            net = RcnnNet()
        net.build_model()

        i = 0

        net.restore_model(sess, model_dir)
        print('restored')

        start_time = time.time()

        npz = np.load('sample.npz')
        print('sample.npz is now loaded')

        im_in, lay_gt, label_gt, names = npz['im'], npz['gt_lay'], npz['gt_label'], npz['names']
        net.set_feed(im_in, lay_gt, label_gt, i)

        pred_class, pred_lay = net.run_result(sess)
        c_out = np.argmax(pred_class, axis=1)
        c_gt = np.argmax(label_gt, axis=1)
        acc = np.mean(np.array(np.equal(c_out, c_gt), np.float32))

        for j in range(batch_size):
            img = im_in[j]
            outim = get_im(img, pred_lay[j], c_out[j], str(j))
            outim2 = get_im(img, lay_gt[j], c_gt[j], str(j))
            outpath = outdir / str(i)

            if not outdir.exists():
                os.makedirs(outpath)

            f, ax = plt.subplots(1, 2)
            ax = iter(ax.flatten())
            plt.sca(next(ax))
            plt.imshow(outim)
            plt.title(f'predicted {j}')
            plt.xlabel(f'class: {c_out[j]}')
            plt.sca(next(ax))
            plt.imshow(outim2)
            plt.title(f'ground truth')
            plt.xlabel(f'class: {c_gt[j]}')
            plt.show()

        print('[step: %d] [time: %s] [acc: %s]' % (i, time.time() - start_time, acc))
        net.print_loss_acc(sess)

and one more change in main:

    if not args.train == -1:
        train(args)
    if not args.test == -1:
        test(args)
    if not args.inference == -1:
        inference(args)

Then I noticed that after each time I run inference i get different results. For example, couple of predictions for image with index 11 in sample.npz:

P.S. I used the following command to run the inference:
python main.py --inference 0 --net vanilla --out_path pretrained_model --gpu 1.

So, the question is how to make results on inference reproducible?

sample.npz lost, could you please reupload it?

Hi!

In your code there exists a trainig.mat file in prepare_data.py line 10 mat='/home/mcg/Data/LSUN/data/training.mat' which isn't explained what exactly it is or how to compose it. Can you elaborate further about it, so that we can try the algorithm?

Thanks!