• 老程

    数据都已经加载好了,但是训练提示空,另外,论坛的搜索功能是否不能正常使用
    日志如下
    INFO 05.28 16:02:33 train_simple.py:42: all characters: 3755
    Model: "sequential"


    Layer (type) Output Shape Param #

    conv2d (Conv2D) (None, 64, 64, 32) 320


    max_pooling2d (MaxPooling2D) (None, 32, 32, 32) 0


    conv2d_1 (Conv2D) (None, 32, 32, 64) 18496


    max_pooling2d_1 (MaxPooling2 (None, 16, 16, 64) 0


    flatten (Flatten) (None, 16384) 0


    dense (Dense) (None, 3755) 61525675

    INFO 05.28 16:02:41 train_simple.py:55: model loaded.
    Total params: 61,544,491
    Trainable params: 61,544,491
    Non-trainable params: 0


    INFO 05.28 16:02:42 train_simple.py:64: passing resume since weights not there. training from scratch
    WARNING:tensorflow:period argument is deprecated. Please use save_freq to specify the frequency in number of samples seen.
    Train for 1024 steps, validate for 1000 steps
    Epoch 1/15000
    WARNING:tensorflow:Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least steps_per_epoch * epochs batches (in this case, 15360000 batches). You may need to use the repeat() function when building your dataset.
    0/1024 [..............................] - ETA: 0sTraceback (most recent call last):
    File "/Applications/PyCharm CE.app/Contents/helpers/pydev/pydevd.py", line 1741, in
    main()
    File "/Applications/PyCharm CE.app/Contents/helpers/pydev/pydevd.py", line 1735, in main
    globals = debugger.run(setup['file'], None, None, is_module)
    File "/Applications/PyCharm CE.app/Contents/helpers/pydev/pydevd.py", line 1135, in run
    pydev_imports.execfile(file, globals, locals) # execute the script
    File "/Applications/PyCharm CE.app/Contents/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
    File "/Users/a10.12/Documents/FOLLOW/ocrcn_tf2-master/train_simple.py", line 120, in
    train()
    File "/Users/a10.12/Documents/FOLLOW/ocrcn_tf2-master/train_simple.py", line 84, in train
    callbacks=callbacks)
    File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow_core/python/keras/engine/training.py", line 728, in fit
    use_multiprocessing=use_multiprocessing)
    File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 324, in fit
    total_epochs=epochs)
    File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow_core/python/keras/engine/training_v2.py", line 180, in run_one_epoch
    aggregator.finalize()
    File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/tensorflow_core/python/keras/engine/training_utils.py", line 140, in finalize
    raise ValueError('Empty training data.')
    ValueError: Empty training data.

    发布在 社区求助区(SOS!!) 阅读更多

与 ManaAI社区 的连接断开,我们正在尝试重连,请耐心等待