keyird / deeplearning-tensorflow2 Goto Github PK

View Code? Open in Web Editor NEW

335.0 335.0 115.0 5.31 MB

本仓库我将使用谷歌TensorFlow2框架逐一复现经典的卷积神经网络：LeNet、AlexNet、VGG系列、GooLeNet、ResNet 系列、DenseNet 系列，以及现在比较经典的目标检测网络、语义分割网络等。

Python 100.00%

deeplearning-tensorflow2's People

Contributors

Stargazers

Watchers

Forkers

qingjiudd annymous-331 hongyunnchen lihude berlingberling xrosliang wuyuchao034 chenzrooo quintus-qi gakkifan2020 2019125078 freewind2016 linhong00316 shibo98 jrcao stq-hydra wangxiaoxian-github wrg-python hhhuuuh wwggpp 13571815901 jason-leeo liuxiaoxiao666 dengjiongshen ignore-create eggandfish lydsss duan-yingjie vedfu fish258 bhnddowinf x-fierce makabakasu andy521 scu-zkgg pubtools linkapp-github tonggett jtyyjyy chaucergit richard1g pengandzhang yfh15882384041 yexiayi jungle8884 xuil0506 jsago laliten jiamery pandihan yangchen123789 shclong newdriverlee newbee955 mintonmu crackercat dk47os3r colleyli josiah1 tang16 ai-framwork dlperf dishamohini 9vivian88 flyingpiginthewind ninespinz guojiaqi123465 heroinqiu mrxrunwuxiwusheng itarvin sfezn1220 shenyiyu1 zy517618 su270 kiwoo1101 fanshaoliang jiranucas yanhuozhuoshi stevewangminchen allen2048 llhcq aspnetcs brq123 xbeeprince hailangzz cherryraining qwerty6518 skyrookieyu moonnnnn1 iwantofun yfh-yufeihu hopebing ma-zenan lihengzhou tzyzrx liweihai hjb89291632 mghdzl jamesgdp classloader

deeplearning-tensorflow2's Issues

whether or not use gpu?

Thanks for your share, i want to ask you that these code can direct run in gpu mode.

Performance issues in 7.%20ResNet/train.py(P2)

Hello,I found a performance issue in 7.%20ResNet/train.py ,
train_db = train_db.shuffle(50000).map was called without num_parallel_calls.
I think it will increase the efficiency of your program if you add this.

The same issues also exist in test_db = test_db.map ,
db = db.shuffle(1000).map,
db = db.shuffle(1000).map,

Here is the documemtation of tensorflow to support this thing.

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

关于损失和准确率不变化的问题

hi, 我使用你的前两个案例进行训练，发现模型输出的损失和准确率都不变

一下输出是第2 个案例，2.快速搭建MNIST分类器/FastNet.py

Epoch 1/20
469/469 [==============================] - 2s 4ms/step - loss: 2.2167 - accuracy: 0.2436
Epoch 2/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 3/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 4/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 5/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044 - val_loss: 2.3584 - val_accuracy: 0.1028
Epoch 6/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 7/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 8/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 9/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 10/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044 - val_loss: 2.3584 - val_accuracy: 0.1028
Epoch 11/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 12/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 13/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 14/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 15/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044 - val_loss: 2.3584 - val_accuracy: 0.1028
Epoch 16/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 17/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 18/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 19/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044
Epoch 20/20
469/469 [==============================] - 2s 4ms/step - loss: 2.3567 - accuracy: 0.1044 - val_loss: 2.3584 - val_accuracy: 0.1028

Performance issues in your project (by P3)

Hello! I've found a performance issue in your project: batch() should be called before map(), which could make your program more efficient. Here is the tensorflow document to support it.

Detailed description is listed below:

/7. ResNet/train.py: .batch(128)(here) should be called before .map(preprocess)(here).
/7. ResNet/train.py: .batch(128)(here) should be called before .map(preprocess)(here).
/4. AlexNet/AlexNet.py: .batch(32)(here) should be called before .map(preprocess)(here).
/5. VGG11/VGG11.py: .batch(16)(here) should be called before .map(preprocess)(here).

Besides, you need to check the function called in map()(e.g., preprocess called in .map(preprocess)) whether to be affected or not to make the changed code work properly. For example, if preprocess needs data with shape (x, y, z) as its input before fix, it would require data with shape (batch_size, x, y, z).

Looking forward to your reply. Btw, I am very glad to create a PR to fix it if you are too busy.

keyird / deeplearning-tensorflow2 Goto Github PK

deeplearning-tensorflow2's People

Contributors

Stargazers

Watchers

Forkers

deeplearning-tensorflow2's Issues

whether or not use gpu?

hi bro，SSD和YOLO还更新吗？

Performance issues in 7.%20ResNet/train.py(P2)

关于损失和准确率不变化的问题

Performance issues in your project (by P3)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent