and the next time,try it with small lr iter: 20 / 70000, total loss: 1.053862 >>> rpn_loss_cls: 0.369174 >>> rpn_loss_box: 0.111182 >>> loss_cls: 0.190974 >>> loss_box: 0.000000 >>> lr: 0.000100...
loss_box: 0.000000 why??????????????
File "/tf-faster-rcnn/tools/../lib/datasets/pascal_voc.py", line 246, in _do_python_eval use_07_metric=use_07_metric, use_diff=self.config['use_diff']) File "/tf-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 122, in voc_eval pickle.dump(recs, f) TypeError: write() argument must be str, not bytes Command exited with non-zero status 1...
./experiments/scripts/test_faster_rcnn.sh $GPU_ID pascal_voc_0712 res101
请问有多个输出的时候怎么办呢？ 求助 下面只是一个输出 cudaMemcpyAsync(out, buffers[1], bufferSize[1], cudaMemcpyDeviceToHost, stream);
有钢筋检测的代码或资源吗？共享一下 我找不到。、
or voc2007?
areas = (x2 - x1) * (y2 - y1) order = scores.argsort()[::-1] keep = [] while order.size > 0: i = order[0] keep.append(i) xx1 = np.maximum(x1[i], x1[order[1:]]) yy1 = np.maximum(y1[i],...