tf-image-segmentation

tf-image-segmentation copied to clipboard

[`labels` out of bound]

3

I am getting the below error in the testing module. > InvalidArgumentError (see above for traceback): assertion failed: [`labels` out of bound] [Condition x < y did not hold element-wise:x...

supriya-godge

I want to freeze the network, but I don't know how to get the name of the output node name.

violet17

OutOfRangeError: RandomShuffleQueue '_1_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 1, current size 0)

20

Hello, I am trying to use the framework to segment images of bacteria. I am using the provided recipe for FCN_32s, but with a few adaptations for my custom data...

FredHaa

Hi, How can I modify the code to be used for semantic segmentation of video frames. I used open-cv to process the frames of the video and basically send each...

ghost

I've tried fully_convolutional_networks.ipynb, but got low contrast images. They are basically all black images.

Senyao-Han

pretrained model with a test image: Invalid Argument and Incompatible Shapes

1

I am trying to run pertained model with a test image. after settling lot of things still I got certain error like InvalidArgumentError (see above for traceback): Incompatible shapes: [1,28,28,21]...

zBabar

From Scratch

1

I am looking for a tutorial or step-by-step instructions including pre-processing, labeling and creation of tfrecords for building an image segmentation pipeline. Any recommendations, especially on the labeling of a...

tjmac

computed output size would be negative

5

I am getting following error when I am running sticker example in Windows 10/Python 3.5/TF 0.1. ``` computed output size would be negative [[Node: fcn_8s/vgg_16/fc6/convolution = Conv2D[T=DT_FLOAT, data_format="NHWC", padding="VALID", strides=[1,...

vijtad

tfrecords should also include depth and format

3

https://github.com/ahundt/tf-image-segmentation/blob/ahundt-keras/tf_image_segmentation/utils/tf_records.py I believe this TFRecord format currently has implicit information including: - number of channels - channel order (bgr vs rgb) Would it be okay to update this to include...

ahundt

Unsuccessful TensorSliceReader constructor: Failed to find any matching files for /home/harsh/Documents/model_fcn8s_final.ckpt

1

`%matplotlib inline from __future__ import division import os import sys import tensorflow as tf import skimage.io as io import numpy as np sys.path.append("/home/harsh/Documents/models/research/slim/") fcn_16s_checkpoint_path = '/home/harsh/Documents/model_fcn8s_final.ckpt' os.environ["CUDA_VISIBLE_DEVICES"] = '1' slim...

Harsh2040