xtudbxk/semantic-segmentation-metrics

this is a project which evaluates the metrics of the network.

semantic-segmentation-metrics's Issues

How to get the segmented image?

By running python deeplab_aspp_test.py,metrics like recall could be got,but how to get and output the segmented image with the trained network model?

如何进行测试集的评估

对您的程序进行复现，只能评估验证集，那测试集的话如何评估

IndexError: boolean index did not match indexed array along dimension 0; dimension is 187500 but corresponding boolean dimension is 562500

I am trying to evaluate your DSRG model however whenever I try to predict results on val.txt files I am getting the below error.

exception info:multiprocessing.pool.RemoteTraceback:
"""
Traceback (most recent call last):
  File "/usr/lib64/python3.6/multiprocessing/pool.py", line 119, in worker
    result = (True, func(*args, **kwds))
  File "/usr/lib64/python3.6/multiprocessing/pool.py", line 44, in mapstar
    return list(map(*args))
  File "/home/ssindhu/winter2020/DSRG-tensorflow/pythonlib/predict.py", line 25, in single_crf_metrics
    m.update(label,crf_pred)
  File "/home/ssindhu/winter2020/DSRG-tensorflow/pythonlib/predict.py", line 120, in update
    self.hist += self._fast_hist(x.flatten(),y.flatten(),self.n_class)
  File "/home/ssindhu/winter2020/DSRG-tensorflow/pythonlib/predict.py", line 116, in _fast_hist
    self.hist = np.bincount( n_class * label_true[mask].astype(int)+label_pred[mask],minlength=n_class**2).reshape(n_class,n_class)
IndexError: boolean index did not match indexed array along dimension 0; dimension is 187500 but corresponding boolean dimension is 562500
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/ssindhu/winter2020/DSRG-tensorflow/pythonlib/predict.py", line 84, in metrics_predict_tf_with_crf
    ret = pool.map(single_crf_metrics,params)
  File "/usr/lib64/python3.6/multiprocessing/pool.py", line 266, in map
    return self._map_async(func, iterable, mapstar, chunksize).get()
  File "/usr/lib64/python3.6/multiprocessing/pool.py", line 644, in get
    raise self._value
IndexError: boolean index did not match indexed array along dimension 0; dimension is 187500 but corresponding boolean dimension is 562500