PaddlePaddle
图片分类模型加载inference模型时报错
环境信息： a. Linux b. Python3.6 c. CUDA10.2/cuDNN 7.6.5 报错信息： InvalidArgumentError: The inverse of Fused batch norm variance should be finite. Found nonfinite values! Please check batch_norm_6.w_2 [Hint: Expected std::isfinite(variance_array[i]) == true, but received std::isfinite(variance_array[i]):0 != true:1.] (at /paddle/paddle/fluid/framework/ir/conv_bn_fuse_pass.cc:101)
当我转换为检测模型时，我得到了同样的错误, , 我使用最新的桨克隆 , 2022.5.9 Release PaddleOCR release/2.5, 我该怎么办，这是我的错误 PaddleOCR/tools/infer/utility.py", line 317, in create_predictor predictor = inference.create_predictor(config) ValueError: (InvalidArgument) The inverse of Fused batch norm variance should be finite. Found nonfinite values! Please check batch_norm_55.w_2 [Hint: Expected std::isfinite(variance_array[i]) == true, but received std::isfinite(variance_array[i]):0 != true:1.] (at /paddle/paddle/fluid/framework/ir/conv_bn_fuse_pass.cc:105)
