时间戳

首页 > 解决方案 > 树莓派上的 CNN 模型

python - 树莓派上的 CNN 模型

问题描述

我正在开展一个涉及在 Raspberry pi 3B 上进行青光眼检测的项目。该模型是在我的笔记本电脑上训练的，文件大小约为 400mb “.h5”。我正在尝试使用 keras 将模型加载到 pi 上 pi 似乎加载了其他较小的模型，但我的却出现了这个错误：

2018-05-15 18:07:04.117054: W tensorflow/core/framework/allocator.cc:101] Allocation of 134217728 exceeds 10% of system memory.
2018-05-15 18:07:05.052281: W tensorflow/core/framework/allocator.cc:101] Allocation of 134217728 exceeds 10% of system memory.
2018-05-15 18:07:05.513437: W tensorflow/core/framework/allocator.cc:101] Allocation of 134217728 exceeds 10% of system memory.
2018-05-15 18:07:06.191609: W tensorflow/core/framework/allocator.cc:101] Allocation of 134217728 exceeds 10% of system memory.
Traceback (most recent call last):
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1322, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1307, in _run_fn
    options, feed_dict, fetch_list, target_list, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1409, in _call_tf_sessionrun
    run_metadata)
tensorflow.python.framework.errors_impl.InternalError: Could not allocate ndarray

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.5/dist-packages/keras/models.py", line 273, in load_model
    topology.load_weights_from_hdf5_group(f['model_weights'], model.layers)
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 3393, in load_weights_from_hdf5_group
    K.batch_set_value(weight_value_tuples)
  File "/usr/local/lib/python3.5/dist-packages/keras/backend/tensorflow_backend.py", line 2377, in batch_set_value
    get_session().run(assign_ops, feed_dict=feed_dict)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 900, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1135, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1316, in _do_run
    run_metadata)
  File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/client/session.py", line 1335, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Could not allocate ndarray

任何帮助，将不胜感激。谢谢！

标签： pythontensorflowmachine-learningraspberry-pikeras

解决方案

构建一个足够大的模型，最终它不适合 1Gb Pi。你在那儿。

你有三个选择：

  1. 建立一个较小的模型，或
  2. 查看是否有可以关闭的非必要服务（例如，如果您没有使用监视器运行，请尝试 Raspian 的服务器安装），或者
  3. 升级到具有更多 RAM 的东西。例如，Asus Tinker 或 Oroid-2 板，它们的大小与 Pi 相同，但具有 2Gb 的 RAM。

推荐阅读