Comments (3)
See more of the issue from GregX999:
Looks like the first time the "deprecated methodology" is introduced is in the "Building an End to End CNN Model" (here: https://academy.zerotomastery.io/courses/1240775/lectures/30615045), but it is used/repeated/referenced multiple times throughout the entire section on CNNs - in many of the videos. The new way to do it would, IMHO, required more than a note however... probably at least another video inserted into the existing ones that went over the new way (I think it's complicated enough for it's own video).
May have to recreate/add a video to showcase different usage (without using tf.keras.preprocessing.image.ImageDataGenerator
.
from tensorflow-deep-learning.
And more again from Pierre:
Of course i can provide you with the number of the video 😉 ...It is the 7th video in Section 5: Computer Vision and CNN with the video number 110. https://www.udemy.com/course/tensorflow-developer-certificate-machine-learning-zero-to-mastery/learn/lecture/25082562#overview
you import the ImageDataGenerator the first time at 2:26
from tensorflow-deep-learning.
From Ashik:
It seems like ImageDataGenerator has been depreciated
https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/image/ImageDataGenerator
Leave a note before lecture 116 explaining this
Stick withtf.data.Dataset
for preprocessing
from tensorflow-deep-learning.
Related Issues (20)
- Error saving the model in Section 8 HOT 6
- initial_epoch value for fine-tuning
- Notebook 05: `TypeError: Unable to serialize [2.0897 2.1129 2.1082] to JSON. Unrecognized type <class 'tensorflow.python.framework.ops.EagerTensor'>` (fix inside) HOT 3
- Notebook 01: pd.get_dummies() resulting in True/False values instead of 1/0 - Causing issues with creating model HOT 15
- Misleading statement about matrix multiplication and dot product HOT 2
- Combining our models (model ensembling/stacking)
- Notebook 10: MASE result for naive not correct
- Notebook 10: Section 309 MASE
- Notebook 10: Section 350 function for making future preds
- TensorBoard.dev is shutting down - find an alternative? HOT 2
- Notebook 02 - `y_test` passed to `model.predict()`, should be `X_test` HOT 1
- Got error on reverting model_2 HOT 1
- MemoryError: Unable to allocate 29.3 GiB for an array with shape (2211861,) and data type <U3551
- Coindesk Bitcoin Data HOT 1
- TensorBoard.dev is shutting down HOT 2
- Invalid Argument Error
- 07 - Food Vision Big - Scikit-learn accuracy poor results
- TextVectorizer and .h5 format
- ZTM Video 111, timestamp 17:00 -> InvalidArgumentError: HOT 1
- Colab does not start New Workbook HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflow-deep-learning.