moelgendy / deep_learning_for_vision_systems Goto Github PK

View Code? Open in Web Editor NEW

307.0 307.0 184.0 180.89 MB

This repository accompanies the book "Deep Learning for Vision Systems".

Jupyter Notebook 96.15% Shell 0.01% Python 3.85%

deep_learning_for_vision_systems's People

Contributors

Stargazers

Watchers

Forkers

avinash-chouhan xm1223 fasladodo wegamekinglc subburajs nguyenquibk1996 superchong1987 aliushn mongkolek lairongxuan chemshi aaronjie millad aminurds itacdonev doctorai-in apanchal abubakarimahmoud hieutrinhds giangdip2410 palash04 chrischamberlin sugarcorn sandeepchopra gridl markusbuchholz darkangelkid phoitack sparsh-ai marctornero vataliya munkyshi pwolf15 eduardolimabra csabdulelah gogoto2 varunmuriyanat zmdemon hany-melad yavuzs3437 ritesh1991 phibsoderso tirendazakademi giakhangluu paulrigor-aws anshpai sathyavikram zfxu rekidiangdata-s azurecloudmonk marcasv ayarzuki mitrofanovdmitry badalahmmed vaibhavthapli shahidul1234 mkkadambi jeremyzyang smartcodes-ai girishgouda16 nataway agamtomar fenice420 mingsterism aaronswei rkgaurav bsp-sp ugsamiz tuanhoang00 bniyaseen vladimirnikiforov ramgtv xiaoting05 smukherjee jdlee0117 suuman kan1shq comvislab fatmaelik drhamedmozaffari jjqv1972 saeed-engr goldenbwuoy alonoak miladshakerdn 2bkool shimul-ostfold guna-venkat pongthepgeo ai-machine-vision-lab furyhawk pjvazquez denny-hwang ghosh-sarbajit faizan8201 mmejiacabello hend-isleem abdom7 srivanoo21 eduardomorales14

deep_learning_for_vision_systems's Issues

Installation

I like the book but can't seem to install the software properly. That is a shame as it detracts from what is otherwise an excellent book! Many similar book suffer from this issue. I think more detail on installation would be very helpful. Is any help available?

data normalization

Hi,
In normalization part of this notebook why do we apply std of train set to test set ? could it be seperated ?

Chapter 3, in cifar10, first dropout must be after Flatten, right? I think dropout use in fully connected block, not in Convolution block!

This is my accuracy when i push dropout(0.3) after Flatten, not Convolution!

[BUG] many `tf.to_float` and `tf.to_int32` should change to `tf.cast`

tf.to_float and tf.to_int32 is no longer available in the tensorflow.

[ERROR] module 'keras.backend' has no attribute 'image_dim_ordering'

The error reads as follows:

/data/dev/cheng/remote/deep_learning_for_vision_systems/chapter_07/ssd_implementatoin_keras/keras_layers/keras_layer_AnchorBoxes.py in call(self, x, mask)
    169 
    170         # We need the shape of the input tensor
--> 171         if K.image_dim_ordering() == 'tf':
    172             batch_size, feature_map_height, feature_map_width, feature_map_channels = x._keras_shape
    173         else: # Not yet relevant since TensorFlow is the only supported backend right now, but it can't harm to have this in here for the future

AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering'

I think this is a version incompatible issue and we should change to use image_data_format

[BUG] many `tf.to_float` and `tf.to_int32` should change to `tf.cast`

tf.to_float and tf.to_int32 is no longer available in the tensorflow.

DCGAN for fashion-MNIST results inaccurate

When the DCGAN Network is trained for 1000 or even 10,000 epochs, the image results are just noise which is kind of consistent in all the images. Typed every line of code at first, tried running the file from the repo afterward, however, the results tend to be the same.

Link given in book in Transfer learning unit is not working

On page 244, the link given in transfer learning unit for the research paper is not working.

moelgendy / deep_learning_for_vision_systems Goto Github PK

deep_learning_for_vision_systems's People

Contributors

Stargazers

Watchers

Forkers

deep_learning_for_vision_systems's Issues

Installation

data normalization

Chapter 3, in cifar10, first dropout must be after Flatten, right? I think dropout use in fully connected block, not in Convolution block!

[BUG] many `tf.to_float` and `tf.to_int32` should change to `tf.cast`

[ERROR] module 'keras.backend' has no attribute 'image_dim_ordering'

[BUG] many `tf.to_float` and `tf.to_int32` should change to `tf.cast`

DCGAN for fashion-MNIST results inaccurate

Link given in book in Transfer learning unit is not working

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