sr_telescope and rec_svtrnet throws inverse op error

[RuohengMa]

• 系统环境/System Environment：Ubuntu 18.04
• 版本号/Version：Paddle：bb3fb69c56ddc8235b6f84325a1802ab9a295bfe PaddleOCR：b3912fcf7a567109a605f6be25a286e78da8952f 问题相关组件/Related components：
• 运行指令/Command Code：python3.7 tools/train.py -c test_tipc/configs/sr_telescope/sr_telescope.yml -o Global.use_cpu=True Global.save_model_dir=./test_tipc/output/sr_telescope/lite_train_lite_infer/norm_train_gpus_0_autocast_null Global.epoch_num=1 Train.loader.batch_size_per_card=16
• 完整报错/Complete Error Message：
• Traceback (most recent call last): File "tools/train.py", line 227, in main(config, device, logger, vdl_writer, seed) File "tools/train.py", line 135, in main model = build_model(config['Architecture']) File "/baidu/xpu/paddle-test/PaddleOCR/ppocr/modeling/architectures/init.py", line 30, in build_model arch = BaseModel(config) File "/baidu/xpu/paddle-test/PaddleOCR/ppocr/modeling/architectures/base_model.py", line 46, in init self.transform = build_transform(config['Transform']) File "/baidu/xpu/paddle-test/PaddleOCR/ppocr/modeling/transforms/init.py", line 30, in build_transform module_class = eval(module_name)(**config) File "/baidu/xpu/paddle-test/PaddleOCR/ppocr/modeling/transforms/tbsrn.py", line 173, in init margins=tuple(tps_margins)) File "/baidu/xpu/paddle-test/PaddleOCR/ppocr/modeling/transforms/tps_spatial_transformer.py", line 122, in init inverse_kernel = paddle.inverse(forward_kernel) File "/usr/local/lib/python3.7/dist-packages/paddle/tensor/math.py", line 2576, in inverse return _C_ops.inverse(x) ValueError: (InvalidArgument) Input is not invertible. [Hint: Expected min_abs_pivot > static_cast<T>(0), but received min_abs_pivot:nan <= static_cast<T>(0):0.] (at /baidu/xpu/paddle-test/Paddle/paddle/phi/kernels/funcs/matrix_inverse.h:53)

我们提供了AceIssueSolver来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide AceIssueSolver to solve issues, do you want it? (Please write yes/no): yes

请尽量不要包含图片在问题中/Please try to not include the image in the issue.