tensorflow_notes

tensorflow_notes copied to clipboard

hi, can i ask why i always occur this problem when i run the code~ many thanks in advance!

zdd0819

0lddriv3r

Where is the module nets?

1

Hi, warmspringwinds,thank you for your share. And there is a problem for me , where i can find the module nets ? For from nets import vgg?

28huasheng

normanheckscher

ValueError: Variable fcn_8s/vgg_16/conv1/conv1_1/weights already exists, disallowed

7

Hi, @warmspringwinds , I followed the steps from [README.md](https://github.com/warmspringwinds/tf-image-segmentation/blob/master/README.md). And start to run the first cell from [fully_convolutional_networks.ipynb](https://github.com/warmspringwinds/tensorflow_notes/blob/master/fully_convolutional_networks.ipynb) . However I got the following ValueError, could you suggest me how...

amiltonwong

In image_segmentation_conditional_random_fields.ipynb, the function softmax_to_unary has deprecated and now unary_from_softmax should be used according to PyDenseCRF (version 2). Reference: (line 82-86) https://github.com/lucasb-eyer/pydensecrf/blob/master/pydensecrf/utils.py 

txzhao

softmax = final_probabilities.squeeze() softmax = processed_probabilities.transpose((2, 0, 1)) i think it should be： processed_probabilities= final_probabilities.squeeze() softmax = processed_probabilities.transpose((2, 0, 1)) am i right?

jabgle

fully_convolutional_networks running error

2

Hi, I clone the notebook files from your git site: `git clone https://github.com/de-code/tensorflow_notes.git` But when I run fully_convolutional_networks.ipynb, there's still an error: > ValueError Traceback (most recent call last) >...

xray1111

Hi, when I try to run your tutorial to make a segmentation with vgg16, I got the result, it's look well. But it's a little different with your result image....

LemonAniLabs

thanks for this helpful ipy notebook with the crf example! this tripped me up, but was a simple fix. thought might be helpful for others. i also have a version...

peteflorence