YOLO 模型：将 m 个示例传递给模型？Tensorflow 问题与占位符

Question

我正在尝试进行迁移学习，以便使用 coursera 深度学习专业的预训练 YOLO 模型。 YOLO 模型进行图像检测和识别：所以我想向该模型添加相同的附加层，以识别检测到的对象的性别。

所以，我有 m 张图像，我尝试将它们传递给现有的 YOLO 模型以获得输出并将这些输出用作新添加层的训练集。这是我的问题发生的地方：当我尝试在一行代码中传递 m 个示例时：我收到错误...

我将详细说明完成的所有步骤和获得的输出：

正在导入库

import argparse
import os
import matplotlib.pyplot as plt
from matplotlib.pyplot import imshow
import scipy.io
import scipy.misc
import numpy as np
import pandas as pd
import PIL
import tensorflow as tf
from keras import backend as K
from keras.preprocessing import image
from keras.layers import Input, Lambda, Conv2D
from keras.models import load_model, Model
from yolo_utils import read_classes, read_anchors, generate_colors, preprocess_image, draw_boxes, scale_boxes
from yad2k.models.keras_yolo import yolo_head, yolo_boxes_to_corners, preprocess_true_boxes, yolo_loss, yolo_body
from keras.models import Sequential
from scipy.misc import imread
get_ipython().magic('matplotlib inline')
import matplotlib.pyplot as plt
import numpy as np
import keras
from keras.layers import Dense
import pandas as pd

%matplotlib inline

正在导入数据集：
2155张形状图片(608,608,3)

train=pd.read_csv("datset.csv",sep=';')
train_img=[]  
for i in range(len(train)):
    (img, train_img_data)=preprocess_image('path_dataset'+train['ImageURL'][i],model_image_size = (608, 608))
    train_img.append(train_img_data)
train_img= np.array(train_img)
train_img=train_img.reshape(2155,608,608,3)

验证数据集维度

print('shape of train_img: ',train_img.shape)
print("shape of first element in train_img: ",train_img[0].shape)
print("reshaping first element in tran_img: ",train_img[0].reshape(1,608,608,3).shape)

数据集维度的输出

shape of train_img: (2155, 608, 608, 3)
shape of first element in train_img:  (608, 608, 3)
reshaping first element in tran_img:  (1, 608, 608, 3)

导入Yolo模型

yolo_model = load_model("model_data/yolo.h5")

为 YOLO 模型提供 train_img 以获得将用作添加层的训练集的输出。

sess = K.get_session()
output=sess.run([yolo_model.output], feed_dict={yolo_model.input: train_img , K.learning_phase(): 0})

我得到的错误：

---------------------------------------------------------------------------
ResourceExhaustedError                    Traceback (most recent call last)
C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
   1360     try:
-> 1361       return fn(*args)
   1362     except errors.OpError as e:

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1339           return tf_session.TF_Run(session, options, feed_dict, fetch_list,
-> 1340                                    target_list, status, run_metadata)
   1341 

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py in __exit__(self, type_arg, value_arg, traceback_arg)
    515             compat.as_text(c_api.TF_Message(self.status.status)),
--> 516             c_api.TF_GetCode(self.status.status))
    517     # Delete the underlying status object from memory otherwise it stays alive

ResourceExhaustedError: OOM when allocating tensor with shape[2155,608,608,32] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
     [[Node: conv2d_1/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_input_1_0_1, conv2d_1/kernel/read)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.


During handling of the above exception, another exception occurred:

ResourceExhaustedError                    Traceback (most recent call last)
<ipython-input-14-067537a70066> in <module>()
      1 sess = K.get_session()
----> 2 output=sess.run([yolo_model.output], feed_dict={yolo_model.input: train_img , K.learning_phase(): 0})

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
    903     try:
    904       result = self._run(None, fetches, feed_dict, options_ptr,
--> 905                          run_metadata_ptr)
    906       if run_metadata:
    907         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1135     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1136       results = self._do_run(handle, final_targets, final_fetches,
-> 1137                              feed_dict_tensor, options, run_metadata)
   1138     else:
   1139       results = []

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1353     if handle is None:
   1354       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1355                            options, run_metadata)
   1356     else:
   1357       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\client\session.py in _do_call(self, fn, *args)
   1372         except KeyError:
   1373           pass
-> 1374       raise type(e)(node_def, op, message)
   1375 
   1376   def _extend_graph(self):

ResourceExhaustedError: OOM when allocating tensor with shape[2155,608,608,32] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
     [[Node: conv2d_1/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_input_1_0_1, conv2d_1/kernel/read)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.


Caused by op 'conv2d_1/convolution', defined at:
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "C:\ProgramData\Anaconda3\lib\runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "C:\ProgramData\Anaconda3\lib\site-packages\traitlets\config\application.py", line 658, in launch_instance
    app.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelapp.py", line 478, in start
    self.io_loop.start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\zmq\eventloop\zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tornado\stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 233, in dispatch_shell
    handler(stream, idents, msg)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\ipkernel.py", line 208, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "C:\ProgramData\Anaconda3\lib\site-packages\ipykernel\zmqshell.py", line 537, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2728, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2850, in run_ast_nodes
    if self.run_code(code, result):
  File "C:\ProgramData\Anaconda3\lib\site-packages\IPython\core\interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-11-c868ea7b7486>", line 7, in <module>
    yolo_model = load_model("model_data/yolo.h5")
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 243, in load_model
    model = model_from_config(model_config, custom_objects=custom_objects)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\models.py", line 317, in model_from_config
    return layer_module.deserialize(config, custom_objects=custom_objects)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\__init__.py", line 55, in deserialize
    printable_module_name='layer')
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py", line 144, in deserialize_keras_object
    list(custom_objects.items())))
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2524, in from_config
    process_node(layer, node_data)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2481, in process_node
    layer(input_tensors[0], **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\topology.py", line 619, in __call__
    output = self.call(inputs, **kwargs)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\layers\convolutional.py", line 168, in call
    dilation_rate=self.dilation_rate)
  File "C:\ProgramData\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 3335, in conv2d
    data_format=tf_data_format)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 781, in convolution
    return op(input, filter)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 869, in __call__
    return self.conv_op(inp, filter)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 521, in __call__
    return self.call(inp, filter)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\nn_ops.py", line 205, in __call__
    name=self.name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\ops\gen_nn_ops.py", line 717, in conv2d
    data_format=data_format, dilations=dilations, name=name)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 3271, in create_op
    op_def=op_def)
  File "C:\ProgramData\Anaconda3\lib\site-packages\tensorflow\python\framework\ops.py", line 1650, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[2155,608,608,32] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
     [[Node: conv2d_1/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_input_1_0_1, conv2d_1/kernel/read)]]
Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocation info.

请注意
输入的占位符大小为 (None,608,608,3) 所以如果我发送大小为 (2155,608,608,3)[ 的数据集=55=] 应该没有问题（就是我看不懂）。除此之外，如果我向网络提供大小为 (1,608,608,3) 的示例，我没有出错！我可以遍历我的 data_set 中的所有元素并为网络提供 2155 次（每次我用 (1,608,608,3) 提供），但这很耗时而且不是最好的方法。
顺便说一句，我认为占位符中的 None 被用来让我可以同时发送 m 个训练示例。

根据输出结果，我真的无法理解错误是什么。我正在等待你的帮助来解决这个问题。

Answer 1

好吧，错误告诉您这是资源耗尽错误。所以你的 ram 很可能是问题所在，因为你似乎没有在 CPU 上训练。一个有 1*608*608*3 个条目的张量比一个有 2155*608*608*3 个条目的张量小得多，所以有你的解释。解决方案很简单：只需使用较小的 batch_size.

进行训练

YOLO 模型：将 m 个示例传递给模型？Tensorflow 问题与占位符

YOLO model: passing m exemples to the model?Tensorflow issue with placeholders

machine-learning

deep-learning

keras

tensorflow

yolo