-
How can I do evaluation in batches as my gpu is running out of memory when I do evaluation?
-
**System information**
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:no
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**:Ubuntu 16…
kanul updated
6 years ago
-
The output size is 256x256 in the example code, in which input's size is 512x512.
I find that there are some differences with official tensorflow version. That version uses dilated convolution(rate…
-
I am using tensorflow version of 1.6, and run the model_test.py, and it got the following error message
```
(/data/virtualE/deeplab) [ug@h40 research]$ python3 -c 'import tensorflow as tf; print(…
-
It is very impressive work. Thanks for sharing it
I am using TiTanX pascal 12GB and I cannot train in your current setting. So, I wonder how much GPU did you use when training? I need reduce the batc…
-
### System information
- **Exact command to reproduce**:
under python3, i ran the code 'deeplab/datasets/build_ade20k_data.py', and get the error 'tf.gfile.FastGFile(filename, 'r').read() error: '…
-
### System information
- **What is the top-level directory of the model you are using**: deeplab
- **Have I written custom code (as opposed to using a stock example script provided in TensorFlow)**:…
-
Is the evaluation done on the complete image size or is the evaluation done on the downsized image ?
For example, if an image is of size (320,240) and the feature map size leading to the softmax is (…
-
Hi, can I run the code on my laptop where I don't have a GPU that supports CUDA? Can you guide me how to make it work? Cheers.
-
I got the following error message when trying to roll back the tensorflow version from 1.7 to 1.6. What might be the cause?
`conda install tensorflow==1.6`
```
Fetching package metadata ......…