TensorFlow 对象检测 API - GitHub

Question

我是 TF 的初学者，我正在尝试运行一些 Tensorflow 对象检测 API：

• GeForce 2GB-MX150
• 16GB 内存
• I7 8550U

我在开始训练时收到以下错误，但我不知道出了什么问题。 我尝试多次更改批量大小等参数，但仍然出现错误。

在this picture 中，您可以看到计算机的总内存和可用内存。

我会感谢你帮助我。

    ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,1024,52,38] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc      [[Node: FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/Conv2D
= Conv2D[T=DT_FLOAT, data_format="NCHW", 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:GPU:0"](FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/Relu, FirstStageFeatureExtractor/resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/weights/read/_2629)]] 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: gradients/FirstStageFeatureExtractor/resnet_v1_101/resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/Conv2D_grad/tuple/control_dependency_1/_3229
= _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_6894_...pendency_1", tensor_type=DT_FLOAT,
_device="/job:localhost/replica:0/task:0/device:CPU:0"]()]] 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.

Answer 1

2 GB 的 GPU 内存对于像 ResNet-101 这样的大型模型来说太少了。