Блог

Всякий раз, когда я пытаюсь извлечь модель из контрольной точки, она выдает ошибку потери данных в Google Colab. Может кто-нибудь помочь мне решить эту проблему? Любая идея, как я могу решить эту проблему.

Ссылка на мой блокнот colab: https://colab.research.google.com/drive/15Cxa9w_PfhJUa9EjizL20yP0sLwIGjNb?usp=sharing

Это мой код для конкретной ячейки, в которой я получаю ошибку

 #Training loop body
with tf.Session() as sess:
    if restore_checkpoint and tf.train.checkpoint_exists(checkpoint_path):
         saver.restore(sess, checkpoint_path)
    else:
        init.run()

    for epoch in range(n_epochs):
        for iteration in range(1, n_iterations_per_epoch   1):
            start = (iteration-1)*batch_size
            stop = iteration*batch_size
            X_batch, y_batch = train_X[start:stop], train_y[start:stop]
            # Run the training operation and measure the loss:
            _, loss_train = sess.run(
                [training_op, loss],
                feed_dict={X: X_batch.reshape([-1, 56, 56, 1]),
                           y: y_batch,
                           mask_with_labels: True})
            print("rIteration: {}/{} ({:.1f}%)  Loss: {:.5f}".format(
                      iteration, n_iterations_per_epoch,
                      iteration * 100 / n_iterations_per_epoch,
                      loss_train),
                  end="")

        # At the end of each epoch, measure the validation loss and accuracy:
        loss_vals = []
        acc_vals = []
        for iteration in range(1, n_iterations_validation   1):
            start = (iteration-1)*batch_size
            stop = iteration*batch_size
            X_batch, y_batch = val_X[start:stop], val_y[start:stop]   
            loss_val, acc_val = sess.run(
                    [loss, accuracy],
                    feed_dict={X: X_batch.reshape([-1, 56, 56, 1]),
                               y: y_batch})
            loss_vals.append(loss_val)
            acc_vals.append(acc_val)
            print("rEvaluating the model: {}/{} ({:.1f}%)".format(
                      iteration, n_iterations_validation,
                      iteration * 100 / n_iterations_validation),
                  end=" " * 10)
        loss_val = np.mean(loss_vals)
        acc_val = np.mean(acc_vals)
        print("rEpoch: {}  Val accuracy: {:.4f}%  Loss: {:.6f}{}".format(
            epoch   1, acc_val * 100, loss_val,
            " (improved)" if loss_val < best_loss_val else ""))

        # And save the model if it improved:
        if loss_val < best_loss_val:
            save_path = saver.save(sess, checkpoint_path)
            best_loss_val = loss_val
 

 WARNING:tensorflow:From <ipython-input-64-7da94f5abe4d>:3: checkpoint_exists (from tensorflow.python.training.checkpoint_management) is deprecated and will be removed in a future version.
Instructions for updating:
Use standard file APIs to check for files with this prefix.
INFO:tensorflow:Restoring parameters from /content/gdrive/MyDrive/brain_tumors/brain_capsule_network/
---------------------------------------------------------------------------
DataLossError                             Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1374     try:
-> 1375       return fn(*args)
   1376     except errors.OpError as e:

7 frames
DataLossError: 2 root error(s) found.
  (0) Data loss: Unable to open table file /content/gdrive/MyDrive/brain_tumors/brain_capsule_network/: Failed precondition: /content/gdrive/MyDrive/brain_tumors/brain_capsule_network; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?
     [[{{node save/RestoreV2}}]]
  (1) Data loss: Unable to open table file /content/gdrive/MyDrive/brain_tumors/brain_capsule_network/: Failed precondition: /content/gdrive/MyDrive/brain_tumors/brain_capsule_network; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?
     [[{{node save/RestoreV2}}]]
     [[save/RestoreV2/_57]]
0 successful operations.
0 derived errors ignored.

During handling of the above exception, another exception occurred:

DataLossError                             Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1392                     'nsession_config.graph_options.rewrite_options.'
   1393                     'disable_meta_optimizer = True')
-> 1394       raise type(e)(node_def, op, message)
   1395 
   1396   def _extend_graph(self):

DataLossError: 2 root error(s) found.
  (0) Data loss: Unable to open table file /content/gdrive/MyDrive/brain_tumors/brain_capsule_network/: Failed precondition: /content/gdrive/MyDrive/brain_tumors/brain_capsule_network; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?
     [[node save/RestoreV2 (defined at <ipython-input-61-e6db6b6cc603>:2) ]]
  (1) Data loss: Unable to open table file /content/gdrive/MyDrive/brain_tumors/brain_capsule_network/: Failed precondition: /content/gdrive/MyDrive/brain_tumors/brain_capsule_network; Is a directory: perhaps your file is in a different file format and you need to use a different restore operator?
     [[node save/RestoreV2 (defined at <ipython-input-61-e6db6b6cc603>:2) ]]
     [[save/RestoreV2/_57]]
0 successful operations.
0 derived errors ignored.

Original stack trace for 'save/RestoreV2':
  File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/usr/local/lib/python3.7/dist-packages/traitlets/config/application.py", line 845, in launch_instance
    app.start()
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelapp.py", line 499, in start
    self.io_loop.start()
  File "/usr/local/lib/python3.7/dist-packages/tornado/platform/asyncio.py", line 132, in start
    self.asyncio_loop.run_forever()
  File "/usr/lib/python3.7/asyncio/base_events.py", line 541, in run_forever
    self._run_once()
  File "/usr/lib/python3.7/asyncio/base_events.py", line 1786, in _run_once
    handle._run()
  File "/usr/lib/python3.7/asyncio/events.py", line 88, in _run
    self._context.run(self._callback, *self._args)
  File "/usr/local/lib/python3.7/dist-packages/tornado/ioloop.py", line 758, in _run_callback
    ret = callback()
  File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 535, in <lambda>
    self.io_loop.add_callback(lambda: self._handle_events(self.socket, 0))
  File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 451, in _handle_events
    self._handle_recv()
  File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
    self._run_callback(callback, msg)
  File "/usr/local/lib/python3.7/dist-packages/zmq/eventloop/zmqstream.py", line 434, in _run_callback
    callback(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/tornado/stack_context.py", line 300, in null_wrapper
    return fn(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
    handler(stream, idents, msg)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/ipkernel.py", line 208, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/usr/local/lib/python3.7/dist-packages/ipykernel/zmqshell.py", line 537, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
    if self.run_code(code, result):
  File "/usr/local/lib/python3.7/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-61-e6db6b6cc603>", line 2, in <module>
    saver = tf.train.Saver(save_relative_paths=True)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 836, in __init__
    self.build()
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 848, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 886, in _build
    build_restore=build_restore)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 516, in _build_internal
    restore_sequentially, reshape)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 336, in _AddRestoreOps
    restore_sequentially)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/saver.py", line 583, in bulk_restore
    return io_ops.restore_v2(filename_tensor, names, slices, dtypes)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 1493, in restore_v2
    name=name)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 750, in _apply_op_helper
    attrs=attr_protos, op_def=op_def)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py", line 3565, in _create_op_internal
    op_def=op_def)
  File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py", line 2045, in __init__
    self._traceback = tf_stack.extract_stack_for_node(self._c_op)