Git Product home page Git Product logo

ocr-gan's Issues

關於論文期刊

您好,根據paperwithcode,
您的論文是目前MVtec benchmark上面,
不使用額外訓練資料以及預訓練網路的條件下,
結果最佳的方法,
想請問為什麼只放在arxiv上而不投稿其他conference或journal呢

basemodel_aug.py里的问题

在get_current_images():方法中,返回值为四个,但在def train_one_epoch(): 接收值为三个
def get_current_images(self): """ Returns current images. Returns: [reals, fakes, fixed] """ reals = self.input_lap.data + self.input_res.data fakes = self.fake.data fake_lap = self.fake_lap.data fake_res = self.fake_res.data return **reals, fakes, fake_lap, fake_res**
def train_one_epoch(self): """ Train the model for one epoch. """ self.netg.train() epoch_iter = 0 for data in tqdm(self.data.train, leave=False, total=len(self.data.train)): self.total_steps += self.opt.batchsize epoch_iter += self.opt.batchsize self.set_input(data) self.optimize_params() if self.total_steps % self.opt.print_freq == 0: errors = self.get_errors() if self.opt.display: counter_ratio = float(epoch_iter) / len(self.data.train.dataset) self.visualizer.plot_current_errors(self.epoch, counter_ratio, errors) if self.total_steps % self.opt.save_image_freq == 0: **reals, fakes, fixed** = self.get_current_images()

gt设置疑问

ocr_gan_aug.py的test中,self.gt_labels设置为异常为0,正常为1。但是异常分数是越高越异常,这样算出来的auc是错误的吧?

关于AUC不一致性的两个问题

  1. 训练过程中,每次epoch都会做一遍test,然后保存最高auc对应的模型参数。但是训练结束后,加载保存的模型参数,重新做test,并不能得到跟train的过程中做的test相同的auc。

  2. test时,使用不同的batch_size会得到差别很大的结果
    @zhangzjn @zju-lyf

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.