Hi there,

First, I wanted to say thanks for sharing! I'm working through the code to help with my own segmentation project and having something to work from is a big help.

Second, I came across a few issues (minor really) that I've figured out and wanted to share:

• TensorFlow 1.0 replaced tf.pack() with tf.stack().
• In TensorFlow 1.0, variables should be initialised using tf.global_variables_initializer()
• In Windows, the os.path.splittext() should use "\ \", rather than '/'. Otherwise, the program can't find any files to pickle (and the MITSceneParsing.pickle file is empty), which in turn means 0 records are found and the feed dict instruction doesn't work.

Like I said, pretty minor stuff, but I wanted to post in case anyone else had any issues.

Best regards,

Frazer

P.S. If you get an out of memory error, it's likely because you're trying to work with 20,000 images, which might be a bit too much. I deleted some of the training images and it worked.

runfile('C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master/FCN.py', wdir='C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master') setting up vgg initialized conv layers ... Setting up summary op... Setting up image reader... Found pickle file! 0 0 Setting up dataset reader Initializing Batch Dataset Reader... {'resize': True, 'resize_size': 224} (0,) (0,) Initializing Batch Dataset Reader... {'resize': True, 'resize_size': 224} (0,) (0,) Setting up Saver... ****************** Epochs completed: 1******************

Traceback (most recent call last):

  File "<ipython-input-1-6062f5716837>", line 1, in <module>
    runfile('C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master/FCN.py', wdir='C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master')

  File "C:\Users\PROCOMP-9\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 866, in runfile
    execfile(filename, namespace)

  File "C:\Users\PROCOMP-9\Anaconda3\lib\site-packages\spyder\utils\site\sitecustomize.py", line 102, in execfile
    exec(compile(f.read(), filename, 'exec'), namespace)

  File "C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master/FCN.py", line 223, in <module>
    tf.app.run()

  File "C:\Users\PROCOMP-9\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 43, in run
    sys.exit(main(sys.argv[:1] + flags_passthrough))

  File "C:/Users/PROCOMP-9/Desktop/FCN.tensorflow-master/FCN.tensorflow-master/FCN.py", line 194, in main
    sess.run(train_op, feed_dict=feed_dict)

  File "C:\Users\PROCOMP-9\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 766, in run
    run_metadata_ptr)

  File "C:\Users\PROCOMP-9\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 943, in _run
    % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))

ValueError: Cannot feed value of shape (0,) for Tensor 'input_image:0', which has shape '(?, 224, 224, 3)'

@shekkizh I took exact code from the git repo and trained without any changes on Titan x for 100000 iterations with default batch size. But on visualizing after completing the training, all i could see is full black images in prediction.

What could possibly go wrong?

Hello,

I was wondering what all is need to be done to get this working with the Pascal dataset. I see that the output placeholder channel size is hardcoded to 1 and the pascal annotations are rgb images so that would need to be changed to 3, along with the number of classes and whatnot. I've tried changing those but its giving me an error in the loss function line and I'm having a hard time understanding how logits which is of shape (?, ?, ?, num_classes) can be compared with y_output which is of shape (?, width, height, channel).

Also a separate question, but do you know how to compute intersection over union for the output?

Thanks

edit: Spent a little bit of time looking around and it looks like I need to figure out how to map the color mapped segmentation labels they give us in the dataset with a 0-20 integer indexed version

Hi! I would like to reproduce your results. Just running the code like python FCN.py doesn't seem to do the job for me. The default parameters are:

• IMAGE_SIZE = 224 ~~(changing it to 256 does not affect the results)~~
• learning_rate = 1e-4
• batch_size = 2

What I get is that training and validation loss start at about 400, and very quickly (200 iterations) decrease until they settle to about 3.

Step: 0, Train_loss:415.754
2016-10-13 12:19:13.407670 ---> Validation_loss: 395.876
Step: 10, Train_loss:28.7208
Step: 20, Train_loss:10.2944
Step: 30, Train_loss:5.06159
Step: 40, Train_loss:4.51668
Step: 50, Train_loss:4.17936
Step: 60, Train_loss:4.55051
Step: 70, Train_loss:4.98752
Step: 80, Train_loss:3.63942
Step: 90, Train_loss:3.56676
Step: 100, Train_loss:3.96641
Step: 110, Train_loss:3.72767
Step: 120, Train_loss:3.26587
Step: 130, Train_loss:3.89015
Step: 140, Train_loss:5.48371
Step: 150, Train_loss:4.27173
Step: 160, Train_loss:3.81378
Step: 170, Train_loss:3.58391
Step: 180, Train_loss:2.79207
Step: 190, Train_loss:4.10269
Step: 200, Train_loss:4.57686
Step: 210, Train_loss:4.00551
Step: 220, Train_loss:3.1667
Step: 230, Train_loss:3.7841
Step: 240, Train_loss:3.74983
Step: 250, Train_loss:3.03212
Step: 260, Train_loss:2.85248
Step: 270, Train_loss:3.64257
Step: 280, Train_loss:3.765
Step: 290, Train_loss:4.16679
Step: 300, Train_loss:4.0291
Step: 310, Train_loss:3.95092
Step: 320, Train_loss:3.38709
Step: 330, Train_loss:2.48646
Step: 340, Train_loss:2.98015
Step: 350, Train_loss:3.59501
Step: 360, Train_loss:3.80755
Step: 370, Train_loss:3.73314
Step: 380, Train_loss:3.40185
Step: 390, Train_loss:3.89394
Step: 400, Train_loss:3.80676
Step: 410, Train_loss:2.78324
Step: 420, Train_loss:3.14695
Step: 430, Train_loss:3.29019
Step: 440, Train_loss:3.16163
Step: 450, Train_loss:3.64598
Step: 460, Train_loss:2.74009
Step: 470, Train_loss:3.93917
Step: 480, Train_loss:3.815
Step: 490, Train_loss:3.83076
Step: 500, Train_loss:4.45192
2016-10-13 12:24:10.606606 ---> Validation_loss: 3.02666

I kept it running up to 35000 iterations, which should be about 3.5 epochs, but the loss won't decrease any further. If I then validate the model at 35000 iterations (Train_loss:2.73392, Validation_loss: 3.51286) with python FCN.py --mode visualize I get always the same prediction, whichever the input image is:

This is also, by the way, the same prediction I get with an earlier model (200 iterations).

Is there something I'm getting wrong? Thank you

----- 7 198 197 196 196 197 196 196 201 197 197 198 190 166 133 130 131 131 132 132 132 132 132 133 133 133 134 129 114 104 96 69 17 10 10 28 124 133 132 132 132 132 132 131 131 131 131 131 130 131 133 132 132 132 133 133 132 132 132 132 132 132 132 132 132 132 132 133 134 133 133 133 133 133 133 133 133 133 133 127 [[Node: entropy/entropy = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](entropy/Reshape, entropy/Reshape_1)]]

This error stoped the traing. Is this related to softmax ? loss = tf.reduce_mean((tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=tf.squeeze(annotation, squeeze_dims=[3]), name="entropy")))

Hi,

I want to use the code to train my own image data. And the data image is 512*512 gray image. But when I train with them, the loss remains nan:

Setting up Saver... Step: 0, Train_loss:nan 2017-03-17 13:55:04.919050 ---> Validation_loss: nan Step: 10, Train_loss:nan Step: 20, Train_loss:nan Step: 30, Train_loss:nan Step: 40, Train_loss:nan

In the py file BatchDatsetReader I changed the way to read images like:

def _read_images(self):
    self.__channels = False
    self.images = np.array(
        [np.expand_dims(self._transform(filename['image']), axis=3) for filename in self.files])

But it did not work

How can I solve this problem to train my gray image ? And what is the mean of NUM_OF_CLASSESS?

I train my dataset which has only two class,so I set the NUM_CLASSES as 2,and the loss turned out to be Nan.I change the NUM _CLASSED to 3 or 151 without changing my dataset,and it can work. I'm very confused with this,please help me.

I have tried to decrease the lr to le-7 and le-8,but it didn't work.

Thanks for sharing your implementation with the public.

I have couple of minor requests to update your code and one real question.

1. how about using 'tqdm' when loading images and annotations or Chainer dataset.
2. the iteration is restarted from 0 when resuming the training. How about using 'blobal-step' variable for fixing this.
3. also again, you 'd better use "os.pathsep" instead of '/' for file separators.

And my main question is.

I trained with the MIT dataset, but the training is not the same as you reported. Train loss and Validation loss starts around 3.5 and does not decrease and just fluctuates. In your report, it seems the loss should goes below 1.0 for convergence, am I right? Step: 860, Train_loss:3.89231 Step: 870, Train_loss:3.64891 Step: 880, Train_loss:2.40985 Step: 890, Train_loss:3.11681 Step: 900, Train_loss:3.55415 Step: 910, Train_loss:3.38955 Step: 920, Train_loss:2.9828 Step: 930, Train_loss:2.39928 Step: 940, Train_loss:3.25557 Step: 950, Train_loss:3.52195 Step: 960, Train_loss:3.15188 Step: 970, Train_loss:5.03387 Step: 980, Train_loss:2.47206 Step: 990, Train_loss:3.91655 Step: 1000, Train_loss:2.78551 2018-03-24 15:37:13.298805 ---> Validation_loss: 3.48481

Looking forwards,

@shekkizh Sorry to bother you but could you please tell me if my number of classes is 2, what all changes need to be done? While training I set NUM_OF_CLASSES as 3. Which one is the annotation file? What changes have to be made in it? Sorry if the question is trivial but I am new to tensorflow. Thanks in advance.

I have run the command "python FCN.py --mode=visualize", but I got result far different from the author's result. Here is my result:

Does anyone know what should I do, and how to apply the whole model in my own dataset and test data set?

Thanks.

I ran the training for a few epoch and was only getting an 'etropy' curve on tensorboard. How can I log and visalise metrics like - accuracy, mean accuracy. mean iou, f.w iou, etc. ?

@shekkizh Kindly help please.

it seems that my own labeled images are not suitable for the feed value. The batch size is 2, 227*227 pixels, single channel labeled pngs, but what is the "4" represent? Hope someone could give me a hint or help me! Will be really appriciate!

BTW, I used Labelme to annotate my own images, and used the Label.png, which are singel channel images directly, is that correct?

Is anyone could share the trained ckpt???thanks!!!! Is anyone could share the trained ckpt???thanks!!!! Is anyone could share the trained ckpt???thanks!!!!

i am new in this field, now i have my dataset and divide is into training and validation. so how i use it to train by this model? where should i correct?