Closed congling closed 2 years ago
在aistudio租赁32G的机器,直接报内存不够
SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError:
Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB.
Please check whether there is any other process using GPU 0.
If no, please decrease the batch size of your model.
(at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221)
图像太大了,压缩自定义图片到1080p以下
------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午9:22 @.>; @.***>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9)
在aistudio租赁32G的机器,直接报内存不够
SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError:
Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB.
Please check whether there is any other process using GPU 0.
If yes, please stop them, or start PaddlePaddle on another GPU.
If no, please decrease the batch size of your model.
(at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221)
— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.***>
我已经压缩到1440x1080了,和第一个帖子一样,直接报CUDNN_STATUS_NOT_SUPPORTED
图像太大了,压缩自定义图片到1080p以下 … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午9:22 @.>; @.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 在aistudio租赁32G的机器,直接报内存不够 SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError: Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB. Please check whether there is any other process using GPU 0. If yes, please stop them, or start PaddlePaddle on another GPU. If no, please decrease the batch size of your model. (at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221) — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.>
确认是32G显存的机器,试下长宽再压缩一半?
------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午10:02 @.>; @.**@.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9)
我已经压缩到1440x1080了,和第一个帖子一样,直接报CUDNN_STATUS_NOT_SUPPORTED
图像太大了,压缩自定义图片到1080p以下 … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午9:22 @.>; @.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 在aistudio租赁32G的机器,直接报内存不够 SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError: Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB. Please check whether there is any other process using GPU 0. If yes, please stop them, or start PaddlePaddle on another GPU. If no, please decrease the batch size of your model. (at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221) — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.>
— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>
确定,是至尊版,压缩到591x443终于行了,不过这解释度也忒低了吧
确认是32G显存的机器,试下长宽再压缩一半? … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午10:02 @.>; @.**@.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 我已经压缩到1440x1080了,和第一个帖子一样,直接报CUDNN_STATUS_NOT_SUPPORTED 图像太大了,压缩自定义图片到1080p以下 … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午9:22 @.>; @.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 在aistudio租赁32G的机器,直接报内存不够 SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError: Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB. Please check whether there is any other process using GPU 0. If yes, please stop them, or start PaddlePaddle on another GPU. If no, please decrease the batch size of your model. (at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221) — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>
显卡很容易炸,但是我试过1920*1080成功的,不是很清楚为什么1440x1080为什么会炸掉
------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午10:18 @.>; @.**@.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9)
确定,是至尊版,压缩到591x443终于行了,不过这解释度也忒低了吧
确认是32G显存的机器,试下长宽再压缩一半? … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午10:02 @.>; @.@.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 我已经压缩到1440x1080了,和第一个帖子一样,直接报CUDNN_STATUS_NOT_SUPPORTED 图像太大了,压缩自定义图片到1080p以下 … ------------------ 原始邮件 ------------------ 发件人: "JiehangXie/PaddleBoBo" @.>; 发送时间: 2022年1月6日(星期四) 上午9:22 @.>; @.>; 主题: Re: [JiehangXie/PaddleBoBo] 自定义头像生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED (Issue #9) 在aistudio租赁32G的机器,直接报内存不够 SystemError: (Fatal) Operator conv2d raises an paddle::memory::allocation::BadAlloc exception. The exception content is :ResourceExhaustedError: Out of memory error on GPU 0. Cannot allocate 38.074219GB memory on GPU 0, 3.777954GB memory has been allocated and available memory is only 27.941284GB. Please check whether there is any other process using GPU 0. If yes, please stop them, or start PaddlePaddle on another GPU. If no, please decrease the batch size of your model. (at /paddle/paddle/fluid/memory/allocation/cuda_allocator.cc:79) . (at /paddle/paddle/fluid/imperative/tracer.cc:221) — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you are subscribed to this thread.Message ID: @.> — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>
— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you commented.Message ID: @.***>
我租了一台8个GPU、单GPU 84G显存的tesla 100,使用缺省头像生成是没问题的。如果使用自动定义头像(我自己的照片,7MB),创建虚拟角色的步骤没有问题(就是生成这个me.mp4),但在生成demo video的时候失败了,报CUDNN_STATUS_NOT_SUPPORTED