lilmangolil

您好，请问训练过后如何在benchmark数据库上检测训练结果的准确率？

31

如题，请问是否是运行/tools/eval.py? 请问第297行fr1 = open('predict_dict.pkl', 'r') 与第298行fr2 = open('gtboxes_dict.pkl', 'r')，这两个pkl文件是指什么呢？如何生成这两个文件？望您回复，感谢！

您好，请问训练中途停止是什么原因呢？

17

所报错误是ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[320992,1962] [[Node: rpn_losses/rpn_minibatch/rpn_find_positive_negative_samples/iou_caculate/Maximum_1 = Maximum[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"](rpn_losses/rpn_minibatch/rpn_find_positive_negative_samples/iou_caculate/split, rpn_losses/rpn_minibatch/rpn_find_positive_negative_samples/iou_caculate/unstack)]] [[Node: gradients/fast_rcnn_roi/Gather_2_grad/Reshape_1/_3699 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_19918_gradients/fast_rcnn_roi/Gather_2_grad/Reshape_1", tensor_type=DT_INT64, _device="/job:localhost/replica:0/task:0/cpu:0"]()]] 非常感谢！

您好，我将tf.nn.sparse_softmax_cross_entropy_with_logits改为focal-loss时出现了以下问题：

1

InvalidArgumentError (see above for traceback): tags and values not the same shape: [] != [256] ，请问怎样解决？谢谢(*^▽^*)