KittiSeg训练train.py问题解决

出现错误 "No variable provide" 

File "train.py", line 131, in 
tf.app.run()
File "/home/emma/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "train.py", line 127, in main
train.do_training(hypes)
File "incl/tensorvision/train.py", line 377, in do_training
tv_graph = core.build_training_graph(hypes, queue, modules)
File "incl/tensorvision/core.py", line 100, in build_training_graph
global_step, learning_rate)
File "/home/emma/fcn/KittiSeg/hypes/../optimizer/generic_optimizer.py", line 91, in training
global_step=global_step)
File "/home/emma/anaconda3/envs/tensorflow/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 529, in apply_gradients
raise ValueError("No variables provided.")
ValueError: No variables provided.

解决：把 generic_optimizer.py 中，79行给成下边的代码：

        if hypes['clip_norm'] > 0:
            #grads, tvars = zip(*grads_and_vars)
            #clip_norm = hypes["clip_norm"]
            #clipped_grads, norm = tf.clip_by_global_norm(grads, clip_norm)
            #grads_and_vars = zip(clipped_grads, tvars)
            clip_norm = hypes["clip_norm"]
            grads_and_vars = [(tf.clip_by_value(grad, -clip_norm, clip_norm), var)
                              for grad, var in grads_and_vars]

出现错误：

2018-08-11 10:52:14.691952: W T:\src\github\tensorflow\tensorflow\core\framework\allocator.cc:108] Allocation of 976453632 exceeds 10% of system memory.
2018-08-11 10:52:14.691951: W T:\src\github\tensorflow\tensorflow\core\framework\allocator.cc:108] Allocation of 976453632 exceeds 10% of system memory.
2018-08-11 10:52:56,763 INFO Step 0/12000: loss = 2.58; lr = 1.00e-05; 1.582 sec (per Batch); 0.6 imgs/sec
2018-08-11 10:53:19.818210: W T:\src\github\tensorflow\tensorflow\core\kernels\queue_base.cc:277] _0_Queues/fifo_queue: Skipping cancelled enqueue attempt with queue not closed
Traceback (most recent call last):
  File "train.py", line 131, in 
    tf.app.run()
  File "d:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
    _sys.exit(main(argv))
  File "train.py", line 127, in main
    train.do_training(hypes)
  File "E:\DeepLearning\KittiSeg\submodules\TensorVision\tensorvision\train.py", line 397, in do_training
    run_training(hypes, modules, tv_graph, tv_sess)
  File "E:\DeepLearning\KittiSeg\submodules\TensorVision\tensorvision\train.py", line 252, in run_training
    _print_eval_dict(eval_names, eval_results, prefix='   (raw)')
  File "E:\DeepLearning\KittiSeg\submodules\TensorVision\tensorvision\train.py", line 164, in _print_eval_dict
    print_str = string.join([nam + ": %.2f" for nam in eval_names],
AttributeError: module 'string' has no attribute 'join'

解决，参考'String' module object has no attribute 'join'改成

print_str = ','.join([nam + ": %.2f" for nam in eval_names])

出现错误：

2018-08-11 11:59:15,270 INFO Running Evaluation Script.
2018-08-11 12:35:05.186763: W T:\src\github\tensorflow\tensorflow\core\kernels\queue_base.cc:277] _0_Queues/fifo_queue: Skipping cancelled enqueue attempt with queue not closed
Traceback (most recent call last):
  File "train.py", line 131, in 
    tf.app.run()
  File "d:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
    _sys.exit(main(argv))
  File "train.py", line 127, in main
    train.do_training(hypes)
  File "E:\DeepLearning\KittiSeg\submodules\TensorVision\tensorvision\train.py", line 396, in do_training
    run_training(hypes, modules, tv_graph, tv_sess)
  File "E:\DeepLearning\KittiSeg\submodules\TensorVision\tensorvision\train.py", line 289, in run_training
    hypes, sess, tv_graph['image_pl'], tv_graph['inf_out'])
  File "E:\DeepLearning\KittiSeg\hypes\../evals/kitti_eval.py", line 139, in evaluate
    for i in xrange(10):
NameError: name 'xrange' is not defined

解决：更改xrange为range