Created by: liushanshan07

Python Call Stacks (More useful to users):

File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/framework.py", line 2423, in append_op attrs=kwargs.get("attrs", None)) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op return self.main_program.current_block().append_op(*args, **kwargs) File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/layers/nn.py", line 8337, in softmax_with_cross_entropy 'axis': axis File "/home/vis/liushanshan/common_env/anaconda2_cuda90_fix_dev/lib/python2.7/site-packages/paddle/fluid/layers/detection.py", line 1543, in ssd_loss conf_loss = nn.softmax_with_cross_entropy(confidence, target_label) File "./train.py", line 199, in parallel_exe loss = fluid.layers.ssd_loss(locs, confs, gt_box, gt_label, box, box_var) File "./train.py", line 374, in pretrained_model=args.pretrained_model)

Error Message Summary:

PaddleCheckError: holder_ should not be null Tensor holds no memory. Call Tensor::mutable_data first. at [/root/Paddle/paddle/fluid/framework/tensor.cc:23] [operator < softmax_with_cross_entropy > error]

报错信息如上，operator < softmax_with_cross_entropy > error