search

Qidian213 / deep_sort_yolov3

Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
GNU General Public License v3.0
1.66k stars 593 forks source link

关于deep-sort yolov3报错 #45

Open AIrobot6 opened 5 years ago

AIrobot6 commented 5 years ago

你好 看到您的关于deep-sort yolov3的文章，下载下来不能正常运行显示报错，Windows 下 Input to reshape is a tensor with 3549 values, but the requested shape requires a multiple of 43095 [[Node:Reshape_75=Reshape[T=DT_FLOAT,Tshape=DT_INT32,_device="/job:localhost/replica:0/task:0/device:CPU:0"](conv2d_59_4/BiasAdd, Reshape_75/shape)]] 一直没有找到问题的根源 特别写了这封邮件 寻求您的帮助，希望您给一些详细的使用教程 期待您的回复。 谢谢

ovgeorge commented 5 years ago

I've trained yolo_v3 on my 3 custom classes and I'm having exactly the same problem with exactly the same "Input to reshape is a tensor with 3549 values, but the requested shape requires a multiple of 43095"

louxy126 commented 5 years ago

Hi @AIrobot6 @ovgeorge same problem with you,have you solved it? InvalidArgumentError (see above for traceback): Input to reshape is a tensor with 43095 values, but the requested shape requires a multiple of 4056 [[Node: Reshape_3 = Reshape[T=DT_FLOAT, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv2d_59/BiasAdd, Reshape_3/shape)]] [[Node: boolean_mask_1/GatherV2/_2847 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_3328_boolean_mask_1/GatherV2", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

ovgeorge commented 5 years ago

@louxy126 check if your number of classes in model file in model_data differ from number of classes in your cfg file

louxy126 commented 5 years ago

@ovgeorge Thank you for your reply. Another problem I encountered was when i load_model： ‘’line 241, in load_model raise ValueError('No model found in config file.') ValueError: No model found in config file. ‘’ Have you ever encountered this? Thanks!