Problems during training

[Waynepoo]

Traceback (most recent call last): File "train.py", line 263, in main() File "train.py", line 217, in main recall, precision, f1 = eval(model, os.path.join(config.output_dir, 'output'), config.testroot, device) File "train.py", line 132, in eval h, w = img.shape[:2] AttributeError: 'NoneType' object has no attribute 'shape' test models: 85%|##########################################################################################################6 | 29/34 [02:08<00:22, 4.44s/it]

[Debugerss]

看一下图片读进去没，如果你是在linux系统下，你最好进文件夹ls一下，看看是否有不是图片的文件

[Waynepoo]

看一下图片读进去没，如果你是在linux系统下，你最好进文件夹ls一下，看看是否有不是图片的文件

谢谢，文件夹中多了一个自动生成的文件，删除解决了，但是在eval函数中（141-150行），boxes_list返回时空，导致报下面的错误：

Traceback (most recent call last): File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 326, in main_evaluation evalData = evaluate_method_fn(p['g'], p['s'], evalParams) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/script.py", line 136, in evaluate_method subm = rrc_evaluation_funcs.load_folder_file(submFilePath, evaluationParams['DET_SAMPLE_NAME_2_ID'], True) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 102, in load_folder_file raise Exception('ZIP entry not valid: %s' % name) Exception: ZIP entry not valid: res_F011912250373_002.txt Traceback (most recent call last): File "train.py", line 265, in main() File "train.py", line 219, in main recall, precision, f1 = eval(model, os.path.join(config.output_dir, 'output'), config.testroot, device) File "train.py", line 151, in eval return result_dict['recall'], result_dict['precision'], result_dict['hmean'] TypeError: string indices must be integers

是我迭代次数太少，导致没有检测到结果吗？ 大神帮忙看看这是什么问题，非常感谢

[15926273249]

请问数据集的格式是怎么样的，可以发一份完整的数据集吗

[hwqgsoso]

你好,请问解决了吗

[hwqgsoso]

TypeError: string indices must be integers

[xunlonghuang]

看一下图片读进去没，如果你是在linux系统下，你最好进文件夹ls一下，看看是否有不是图片的文件

谢谢，文件夹中多了一个自动生成的文件，删除解决了，但是在eval函数中（141-150行），boxes_list返回时空，导致报下面的错误：

Traceback (most recent call last): File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 326, in main_evaluation evalData = evaluate_method_fn(p['g'], p['s'], evalParams) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/script.py", line 136, in evaluate_method subm = rrc_evaluation_funcs.load_folder_file(submFilePath, evaluationParams['DET_SAMPLE_NAME_2_ID'], True) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 102, in load_folder_file raise Exception('ZIP entry not valid: %s' % name) Exception: ZIP entry not valid: res_F011912250373_002.txt Traceback (most recent call last): File "train.py", line 265, in main() File "train.py", line 219, in main recall, precision, f1 = eval(model, os.path.join(config.output_dir, 'output'), config.testroot, device) File "train.py", line 151, in eval return result_dict['recall'], result_dict['precision'], result_dict['hmean'] TypeError: string indices must be integers

是我迭代次数太少，导致没有检测到结果吗？ 大神帮忙看看这是什么问题，非常感谢

您好，请问您这个问题是否解决了呢？

[xunlonghuang]

看一下图片读进去没，如果你是在linux系统下，你最好进文件夹ls一下，看看是否有不是图片的文件

谢谢，文件夹中多了一个自动生成的文件，删除解决了，但是在eval函数中（141-150行），boxes_list返回时空，导致报下面的错误：

Traceback (most recent call last): File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 326, in main_evaluation evalData = evaluate_method_fn(p['g'], p['s'], evalParams) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/script.py", line 136, in evaluate_method subm = rrc_evaluation_funcs.load_folder_file(submFilePath, evaluationParams['DET_SAMPLE_NAME_2_ID'], True) File "/mnt/data/ocr/psenet/PSENet.pytorch-master/cal_recall/rrc_evaluation_funcs.py", line 102, in load_folder_file raise Exception('ZIP entry not valid: %s' % name) Exception: ZIP entry not valid: res_F011912250373_002.txt Traceback (most recent call last): File "train.py", line 265, in main() File "train.py", line 219, in main recall, precision, f1 = eval(model, os.path.join(config.output_dir, 'output'), config.testroot, device) File "train.py", line 151, in eval return result_dict['recall'], result_dict['precision'], result_dict['hmean'] TypeError: string indices must be integers

是我迭代次数太少，导致没有检测到结果吗？ 大神帮忙看看这是什么问题，非常感谢

这个问题的原因是因为数据集格式没有按照Readme里面说的格式而产生的，可以修改数据集格式，或者修改script.py里default_evaluation_params里面的匹配规则。

[zzzzjx]

请问如何修改训练任意点训练呢

[aojue1109]

Exception: ZIP entry not valid

这个确实是script.py里面的正则表达式问题，建议在里面写一个main函数，跑一下自己的数据集，看看是否都能够通过验证；比如我的修改为： ef default_evaluation_params(): """ default_evaluation_params: Default parameters to use for the validation and evaluation. """ return { 'IOU_CONSTRAINT': 0.5, 'AREA_PRECISION_CONSTRAINT': 0.5, # 'GT_SAMPLE_NAME_2_ID': 'gt_img_([0-9]+).txt', 'GT_SAMPLE_NAME_2_ID': 'gt_img_(.).txt', # 'DET_SAMPLE_NAME_2_ID': 'res_img_([0-9]+).txt', 'DET_SAMPLE_NAME_2_ID': 'res_img_(.).txt', 'LTRB': False, # LTRB:2points(left,top,right,bottom) or 4 points(x1,y1,x2,y2,x3,y3,x4,y4) 'CRLF': False, # Lines are delimited by Windows CRLF format 'CONFIDENCES': False, # Detections must include confidence value. AP will be calculated 'PER_SAMPLE_RESULTS': True # Generate per sample results and produce data for visualization } 图片的命名规则将不局限于数字，自己可根据实际修改