如何解決TensorFlow中的'BiasGrad requires tensor size <= int32 max' InvalidArgumentError？

Question

我正在嘗試使用 Keras/Tensorflow 訓練卷積神經網絡。 我的模型編譯正確，但是一旦開始訓練，就會返回以下錯誤：

Using TensorFlow backend.

Epoch 1/3

Traceback (most recent call last):
  File "./main.py", line 17, in <module>
    history = CNN.fit(TrainImages, TrainMasks, epochs = 3)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/keras/engine/training.py", line 1239, in fit
    validation_freq=validation_freq)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/keras/engine/training_arrays.py", line 196, in fit_loop
    outs = fit_function(ins_batch)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/keras/backend.py", line 3727, in __call__
    outputs = self._graph_fn(*converted_inputs)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 1551, in __call__
    return self._call_impl(args, kwargs)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 1591, in _call_impl
    return self._call_flat(args, self.captured_inputs, cancellation_manager)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 1692, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/eager/function.py", line 545, in call
    ctx=ctx)

  File "/home/tomhalmos/.local/lib/python3.6/site-packages/tensorflow_core/python/eager/execute.py", line 67, in quick_execute
    six.raise_from(core._status_to_exception(e.code, message), None)

  File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.**InvalidArgumentError:  BiasGrad requires tensor size <= int32 max**
         [[node gradients/conv2d_22/BiasAdd_grad/BiasAddGrad (defined at /home/tomhalmos/.local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_5496]

Function call stack:
keras_scratch_graph

如果以上內容還不夠，我們很樂意提供任何進一步的細節。

Answer 1

邊界檢查是針對張量中元素的數量。 大小限制為 21.47 億個值 ( int32 )。

將圖像大小 (hxv) 乘以樣本批量大小。 將其乘以操作中的通道數（例如 Conv2D）。 計數大於 2.1e9 的地方是有罪操作。 除了減少其中一個數字之外，我看不到任何解決方案。

Answer 2

我改變了我在 GPU 上的工作，它運行良好。