I am under the impression that TF only supports CUDA. From my research, the only way to get it to support OpenCL and AMD GPUs is to get a separate “adapter” module such as TF Coriander and suffer through the performance failure: From the GitHub: for the recurrent networks, Coriander is around 4 times slower … Read more
The mnist object is returned from the read_data_sets() function defined in the tf.contrib.learn module. The mnist.train.next_batch(batch_size) method is implemented here, and it returns a tuple of two arrays, where the first represents a batch of batch_size MNIST images, and the second represents a batch of batch-size labels corresponding to those images. The images are returned … Read more
I too got the same problem. I downloaded get-pip.py from https://bootstrap.pypa.io/get-pip.py and then ran python2.7 get-pip.py for installing pip2.7. And then ran the pip install command with python2.7 as follows. For Ubuntu/Linux: For Mac OS X: This should work just fine as it did for me 🙂 I followed these instructions from here.
I have tensorflow 1.2.1 installed, and I need to downgrade it to version 1.1 to run a specific tutorial. What is the safe way to do it? I am using windows 10, python 3.5. Tensorflow was installed with pip3, but “pip3 show tensorflow” returns blank. Is it possible to have multiple version of tensorflow on … Read more
You either need a “def main(args)” function in your file: or tf.app.run() can call an external function
A better (recommended) alternative is to create a virtual environment of the desired Python version and then use that environment to run Tensorflow and other scripts. To do that, you can follow the instructions given here. BUT, if you don’t want to create a separate environment, then conda install python=<version> should do. OR (not recommended) you can download the … Read more
Check: /usr/local/lib/python3.5/dist-packages You’ll either have Pip there or easy_install(part of Pythons setup tools), which can be used to install Pip: Or you can try: Another option is attempting to install from a repository, the package name depends on your distribution: Edit: Try this correction for easy install: I’m assuming that’s the directory it’s installed to. Also, … Read more
Seems like this is due to pandas version higher than 0.21.0 and numpy version 1.13.3 that is pulled by TensorFlow not playing well together. Here is how I fixed it in my end:
I’ll give an example to make it clearer: x: input image of shape [2, 3], 1 channel valid_pad: max pool with 2×2 kernel, stride 2 and VALID padding. same_pad: max pool with 2×2 kernel, stride 2 and SAME padding (this is the classic way to go) The output shapes are: valid_pad: here, no padding so the output … Read more
You need to install tqdm module, you can do it by using python pip. for more info tqdm