pytorch-captcha-recognition
pytorch-captcha-recognition copied to clipboard
dee1024
基于CNN训练的一套 "端到端" 的验证码识别模型，使用深度学习+训练数据+大量计算力，纯数字识别率高达 99.99%，数字+字母识别率 96%
Traceback (most recent call last): File "/Users/haiyuan/Downloads/pytorch-captcha-recognition-master-2/captcha_train.py", line 43, in main() File "/Users/haiyuan/Downloads/pytorch-captcha-recognition-master-2/captcha_train.py", line 23, in main for i, (images, labels) in enumerate(train_dataloader): File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 346, in __next__ data...
pytorch-captcha-recognition git:(master) ✗ python captcha_train.py init net ('epoch:', 0, 'step:', 0, 'loss:', 0.7110539674758911) ('epoch:', 1, 'step:', 0, 'loss:', 0.20382478833198547) ('epoch:', 2, 'step:', 0, 'loss:', 0.2277430146932602) ('epoch:', 3, 'step:', 0, 'loss:',...
epoch: 0 step: 9 loss: 0.18992629647254944 epoch: 0 step: 19 loss: 0.1413472294807434 epoch: 0 step: 29 loss: 0.13513770699501038 epoch: 0 step: 39 loss: 0.13097789883613586 epoch: 0 step: 49 loss: 0.13270880281925201...
图片大小设置
RuntimeError: size mismatch, m1: [64 x 8960], m2: [1344 x 1024] at /pytorch/aten/src/TH/generic/THTensorMath.cpp:940 设置了自己定义的图片大小后出现不匹配的错误，请问如何解决？
