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：所以我想在这个模型中添加相同的附加层，以识别检测到的对象的性别。
因此，我有 m 个图像，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：我收到一个错误...
我将指定完成的所有步骤和获得的输出：
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
导入数据集：
2155张形状图像（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")
用 train_img 输入 YOLO 模型以获得输出，该输出将用作添加层的训练集。
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
输入的占位符是大小（None,608,608,3）所以如果我发送一个大小为（2155,608,608,3）的数据集应该没有问题（这就是我无法理解的）。除此之外，如果我给网络提供一个大小为(1,608,608,3)的示例，我没有错误！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) 提供它），但这很耗时，而且不是最好的方法。
顺便说一句，我认为使用占位符中的 None 以便我可以同时发送 m 个训练示例。
根据输出，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。