Reid訓練後執行vail失敗問題

[qa717415]

您好，我們在執行reid模型時，epoch=60個訓練的途中,於第59個epoch出現錯誤
以下是錯誤訊息
Exception during training:
Traceback (most recent call last):
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 133, in _compile_dependencies
from .rank_cylib.rank_cy import evaluate_cy
ModuleNotFoundError: No module named 'fast_reid.fastreid.evaluation.rank_cylib.rank_cy'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File ".\fast_reid\fastreid\engine\train_loop.py", line 151, in train
self.after_epoch()
File ".\fast_reid\fastreid\engine\train_loop.py", line 185, in after_epoch
h.after_epoch()
File ".\fast_reid\fastreid\engine\hooks.py", line 377, in after_epoch
self._do_eval()
File ".\fast_reid\fastreid\engine\hooks.py", line 351, in _do_eval
results = self._func()
File ".\fast_reid\fastreid\engine\defaults.py", line 305, in test_and_save_results
self._last_eval_results = self.test(self.cfg, self.model)
File ".\fast_reid\fastreid\engine\defaults.py", line 434, in test
data_loader, evaluator = cls.build_evaluator(cfg, dataset_name)
File ".\fast_reid\fastreid\engine\defaults.py", line 417, in build_evaluator
return data_loader, ReidEvaluator(cfg, num_query, output_dir)
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 35, in init
self._compile_dependencies()
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 138, in compile_dependencies
compile_helper()
File ".\fast_reid\fastreid\evaluation\rank_cylib_init.py", line 15, in compile_helper
ret = subprocess.run(["make", "-C", path])
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 488, in run
with Popen(*popenargs, **kwargs) as process:
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 800, in init
restore_signals, start_new_session)
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 1207, in _execute_child
startupinfo)
FileNotFoundError: [WinError 2] 系統找不到指定的檔案。
Traceback (most recent call last):
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 133, in _compile_dependencies
from .rank_cylib.rank_cy import evaluate_cy
ModuleNotFoundError: No module named 'fast_reid.fastreid.evaluation.rank_cylib.rank_cy'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "fast_reid/tools/train_net.py", line 60, in
args=(args,),
File ".\fast_reid\fastreid\engine\launch.py", line 71, in launch
main_func(*args)
File "fast_reid/tools/train_net.py", line 47, in main
return trainer.train()
File ".\fast_reid\fastreid\engine\defaults.py", line 350, in train
super().train(self.start_epoch, self.max_epoch, self.iters_per_epoch)
File ".\fast_reid\fastreid\engine\train_loop.py", line 151, in train
self.after_epoch()
File ".\fast_reid\fastreid\engine\train_loop.py", line 185, in after_epoch
h.after_epoch()
File ".\fast_reid\fastreid\engine\hooks.py", line 377, in after_epoch
self._do_eval()
File ".\fast_reid\fastreid\engine\hooks.py", line 351, in _do_eval
results = self._func()
File ".\fast_reid\fastreid\engine\defaults.py", line 305, in test_and_save_results
self._last_eval_results = self.test(self.cfg, self.model)
File ".\fast_reid\fastreid\engine\defaults.py", line 434, in test
data_loader, evaluator = cls.build_evaluator(cfg, dataset_name)
File ".\fast_reid\fastreid\engine\defaults.py", line 417, in build_evaluator
return data_loader, ReidEvaluator(cfg, num_query, output_dir)
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 35, in init
self._compile_dependencies()
File ".\fast_reid\fastreid\evaluation\reid_evaluation.py", line 138, in compile_dependencies
compile_helper()
File ".\fast_reid\fastreid\evaluation\rank_cylib_init.py", line 15, in compile_helper
ret = subprocess.run(["make", "-C", path])
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 488, in run
with Popen(*popenargs, **kwargs) as process:
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 800, in init
restore_signals, start_new_session)
File "C:\Users\adm\anaconda3\envs\botsort\lib\subprocess.py", line 1207, in _execute_child
startupinfo)
FileNotFoundError: [WinError 2] 系統找不到指定的檔案。

我們不清楚,其中ModuleNotFoundError: No module named 'fast_reid.fastreid.evaluation.rank_cylib.rank_cy'
這段訊息所提出的rank_cy檔案中,為何無法讀取到?

[ricky-696]

哈囉~

根據下面的Code

AICUP_Baseline_BoT-SORT/fast_reid/fastreid/evaluation/reid_evaluation.py

Lines 128 to 142 in cad9df1

	def _compile_dependencies(self):
	# Since we only evaluate results in rank(0), so we just need to compile
	# cython evaluation tool on rank(0)
	if comm.is_main_process():
	try:
	from .rank_cylib.rank_cy import evaluate_cy
	except ImportError:
	start_time = time.time()
	logger.info("> compiling reid evaluation cython tool")
	compile_helper()
	logger.info(
	">>> done with reid evaluation cython tool. Compilation time: {:.3f} "
	"seconds".format(time.time() - start_time))

我猜測你應該在安裝環境時沒有確實進行Installation的Step.6與Step.7

你可以看看模型輸出的Log有沒有compiling reid evaluation cython tool相關的文字，如果有就代表我上面的猜測是對的。