摘要(Abstract)
智能ECN(Edge Computing Node)兼容多种异构联接、支持实时处理与响应、提供软硬一体化安全等;
边缘计算参考架构在每层提供了模型化的开放接口,实现了架构的全层次开放;边缘计算参考架构通过纵向管理服务、数据全生命周期服务、安全服务,实现业务的全流程、全生命周期的智能服务。
相关应用
云卸载:在传统的内容分发网络中,数据都会缓存到边缘结点。随着物联网的发展,数据的生产和消费都是在边缘结点,也就是说边缘结点也需要承担一定的计算任务。把云中心的计算任务卸载到边缘结点这个过程叫做云卸载。
视频分析
智慧城市:对基于位置的一些应用来说,边缘计算的性能要由于云计算。比如导航,终端设备可以根据自己的实时位置把相关位置信息和数据交给边缘结点来进行处理,边缘结点基于现有的数据进行判断决策。整个过程中的网络开销都是最小的。用户请求得以极快的得到响应。
智能家居。。。
相关技术
边缘协作:利用多个边缘结点协同合作,创建一个虚拟的共享数据的视图,利用一个预定义的公共服务接口来将这些数据进行整合。同时通过这个接口,我们可以编写应用程序为用户提供更复杂的服务
---------------------
作者:EmilyGnn
来源:CSDN
原文:https://blog.csdn.net/gaoruowen1/article/details/82780073
版权声明:本文为博主原创文章,转载请附上博文链接!
主题(Topic)
项目(Project)
mkoura/browser-suspender
VladKarpushin/out_of_focus_deblur
jollheef/out-of-tree
madebyfabian/vue-focus-visible
wx-component
fanig01/frutaefruto
master801/Out-of-Translation
spencermountain/out-of-character
y2bd/out-of-sorts
MrSimsek/out-of-home
InfiniteIntel/Out-Of-Body
LukeShirnia/out-of-memory
out-of-cheese-error/astrochelys
test_main() File "cnn_test_auto.py", line 119, in test_main loss,acuracy = test(data_path,generate_test, model_path) File "cnn_test_auto.py", line 76, in test loss, accuracy = my_spatial_model.evaluate_generator(generate_test, steps=test_step) #98需要才能重新确定值的大小 File "D:\python 3.6.4\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "D:\python 3.6.4\lib\site-packages\keras\engine\training.py", line 1472, in evaluate_generator verbose=verbose) File "D:\python 3.6.4\lib\site-packages\keras\engine\training_generator.py", line 346, in evaluate_generator outs = model.test_on_batch(x, y, sample_weight=sample_weight) File "D:\python 3.6.4\lib\site-packages\keras\engine\training.py", line 1256, in test_on_batch outputs = self.test_function(ins) File "D:\python 3.6.4\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__ return self._call(inputs) File "D:\python 3.6.4\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call fetched = self._callable_fn(*array_vals) File "D:\python 3.6.4\lib\site-packages\tensorflow\python\client\session.py", line 1439, in __call__ run_metadata_ptr) File "D:\python 3.6.4\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__ c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[128,64,1,1] and type float on /job :localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[{{node block2_sepconv1_1/separable_conv2d}}]] 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. [[{{node metrics_33/acc/Mean_1}}]] 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." class="topic-tag topic-tag-link">
out-of-GPU-memoery
focus
ImBearChild/SiplPen
yirami/LMMS-out-of-date
out-of-cheese-error/gooseberry
out-of-my-mind/RedisAndSession
out-of-my-mind/UpdateCssLink
theDavidBarton/out-of-the-blue
godaddy/out-of-band-cache
out-of-cheese-error/mars2020api
Jessseee/Fish-Out-of-Water
StAC-VEX/Out-of-Control
simon04/aur-out-of-date
out-of-my-mind/GetHolidays
shellyln/out-of-proc-server
out-of-cheese-error/quoth
tcassanelli/pyoof
全部项目