make: 进入目录“/home/rwd/graduate/code/fots.PyTorch-master/utils/lanms” g++ -o adaptor.so -I include -std=c++11 -O3 -I/home/rwd/anaconda2/envs/py351/include/python3.5m -I/home/rwd/anaconda2/envs/py351/include/python3.5m -Wno-unused-result -Wsign-compare -march=nocona -mtune=haswell -ftree-vectorize -fPIC -fstack-protector-strong -fno-plt -O3 -pipe -fdebug-prefix-map==/usr/local/src/conda/- -fdebug-prefix-map==/usr/local/src/conda-prefix -fuse-linker-plugin -ffat-lto-objects -flto-partition=none -flto -DNDEBUG -fwrapv -O3 -Wall -Wstrict-prototypes -L/home/rwd/anaconda2/envs/py351/lib/python3.5/config-3.5m -L/home/rwd/anaconda2/envs/py351/lib -lpython3.5m -lpthread -ldl -lutil -lrt -lm -Xlinker -export-dynamic adaptor.cpp include/clipper/clipper.cpp --shared -fPIC g++: 错误：unrecognized command line option ‘-fno-plt’ make: *** [adaptor.so] 错误 1 make: 离开目录“/home/rwd/graduate/code/fots.PyTorch-master/utils/lanms” Traceback (most recent call last): File "train.py", line 14, in from trainer import Trainer File "/home/rwd/graduate/code/fots.PyTorch-master/trainer/init.py", line 1, in from .trainer import * File "/home/rwd/graduate/code/fots.PyTorch-master/trainer/trainer.py", line 4, in from utils.bbox import Toolbox File "/home/rwd/graduate/code/fots.PyTorch-master/utils/bbox.py", line 8, in from . import lanms File "/home/rwd/graduate/code/fots.PyTorch-master/utils/lanms/init.py", line 8, in raise RuntimeError('Cannot compile lanms: {}'.format(BASE_DIR)) RuntimeError: Cannot compile lanms: /home/rwd/graduate/code/fots.PyTorch-master/utils/lanms

用的是SynthText数据集，训练时出现：

RankWarning: Polyfit may be poorly conditioned 
edge = fit_line([p0[0], p1[0]], [p0[1], p1[1]])

上面的警告不影响训练，训练一段时间后loss出现Nan值。我并没有执行build.sh这个程序，因为学校集群环境中没有NVCC。看其他问题中提到好像也不需要编译它。 希望问题能得到解决。

Hi, many thanks to your great contribution! When I finished training and save the model using "torch.save()", I get the follow problem: [can't pickle _thread.RLock objects] I use python3.6 and torch 1.0.0, it seems that something wrong with the model structure? Do you have any suggestion? thanks for your reply!

不是很明白下面这个函数的作用，可以简单讲解一下吗？ def param2theta(param, w, h): param = np.vstack([param, [0, 0, 1]]) param = np.linalg.inv(param)

    theta = np.zeros([2, 3])
    theta[0, 0] = param[0, 0]
    theta[0, 1] = param[0, 1] * h / w
    theta[0, 2] = param[0, 2] * 2 / w + theta[0, 0] + theta[0, 1] - 1
    theta[1, 0] = param[1, 0] * w / h
    theta[1, 1] = param[1, 1]
    theta[1, 2] = param[1, 2] * 2 / h + theta[1, 0] + theta[1, 1] - 1
    return theta

Hi @jiangxiluning thank you for sharing the code. I have recently read the paper but I cannot understand the Eqn. (4-8) in the FOTS paper. The equations are as follows:

From them, to compute the M matrix, we need to compute tx, ty, which are both related to the x,y position (from Eqn 4 and 5). So does that mean there is one M matrix for each point (x,y) in the input feature map? But as far as I know, for one bounding box, we just need one transformation matrix, right? Do I miss something or understand uncorrectly? Looking forward to your reply, thanks a lot!

@jiangxiluning thank you for your hard work.

Can you share some documentation on:

• Preparing the training data.
• How to train
• How to use the model.

Thank you waiting for your reply

Hi, I've met a crash while running training model. There is a problem from pytorch_lightning, maybe. But I don't understand why 'self.log' cannot be used. Please help me to solve the problem.

I ran the project on the colab. The version of the pytorch_lightening is 1.5.

Traceback (most recent call last): File "train.py", line 99, in main(config, args.resume) File "train.py", line 75, in main trainer.fit(model=model, datamodule=data_module) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 769, in fit self._fit_impl, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 719, in _call_and_handle_interrupt return self.strategy.launcher.launch(trainer_fn, *args, trainer=self, **kwargs) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93, in launch return function(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 809, in _fit_impl results = self._run(model, ckpt_path=self.ckpt_path) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 1234, in _run results = self._run_stage() File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 1321, in _run_stage return self._run_train() File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/trainer.py", line 1351, in _run_train self.fit_loop.run() File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/loops/base.py", line 204, in run self.advance(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/loops/fit_loop.py", line 268, in advance self._outputs = self.epoch_loop.run(self._data_fetcher) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/loops/base.py", line 204, in run self.advance(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 246, in advance self.trainer._logger_connector.update_train_step_metrics() File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/connectors/logger_connector/logger_connector.py", line 197, in update_train_step_metrics self._log_gpus_metrics() File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/trainer/connectors/logger_connector/logger_connector.py", line 226, in _log_gpus_metrics key, mem, prog_bar=False, logger=True, on_step=True, on_epoch=False File "/usr/local/lib/python3.7/dist-packages/pytorch_lightning/core/lightning.py", line 386, in log "You are trying to self.log() but it is not managed by the Trainer control flow" pytorch_lightning.utilities.exceptions.MisconfigurationException: You are trying to self.log() but it is not managed by the Trainer control flow

When I run bash build.sh, I get

rroi_align_kernel.cu:1:10: fatal error: torch/extension.h: No such file or directory
    1 | #include <torch/extension.h>

How to resolve this problem?

epoch          : 1
loss           : 0.03228356248388688
precious       : 0.0
recall         : 0.0
hmean          : 0.0
val_precious   : 0.0
val_recall     : 0.0
val_hmean      : 0.0

can someone help me

I'm training and checking the results. Drawing a box on an image file is going well. I want to check the recognition result of the text, which code are checking the result?

python eval.py Traceback (most recent call last): File "eval.py", line 10, in from model.model import FOTSModel File "/Users/zakj/Desktop/work/detection_fots/model/model.py", line 6, in import pretrainedmodels as pm ModuleNotFoundError: No module named 'pretrainedmodels'

ERROR: Could not install packages due to an OSError: [Errno 2] No such file or directory: '/home/conda/feedstock_root/build_artifacts/absl-py_1615404881292/work'

absl-py @ file:///home/conda/feedstock_root/build_artifacts/absl-py_1615404881292/work aiohttp==3.7.4.post0 async-timeout==3.0.1 attrs @ file:///tmp/build/80754af9/attrs_1604765588209/work

beacause of the "@ file:///home/conda/feedstock_root/build_artifacts/absl-py_1615404881292/work"?

ImportError: /opt/conda/lib/python3.6/site-packages/rotate_roi-0.0.0-py3.6-linux-x86_64.egg/rotated_roi.cpython-36m-x86_64-linux-gnu.so: undefined symbol: RROIAlignForwardLaucher

env:

`[07/26 03:17:38 LP]: Environment info:

sys.platform linux Python 3.6.9 |Anaconda, Inc.| (default, Jul 30 2019, 19:07:31) [GCC 7.3.0] numpy 1.18.1 PyTorch 1.6.0 @/opt/conda/lib/python3.6/site-packages/torch PyTorch debug build False GPU available True GPU 0,1,2 GeForce RTX 2080 Ti CUDA_HOME /usr/local/cuda TORCH_CUDA_ARCH_LIST 5.2 6.0 6.1 7.0 7.5+PTX Pillow 8.4.0 torchvision 0.7.0 @/opt/conda/lib/python3.6/site-packages/torchvision torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75 cv2 3.4.1

PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) Math Kernel Library Version 2019.0.5 Product Build 20190808 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 10.2
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75
• CuDNN 7.6.5
• Magma 2.5.2
• Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, `