fathom icon indicating copy to clipboard operation
fathom copied to clipboard

Reference workloads for modern deep learning methods.

Results 22 fathom issues
Sort by recently updated
recently updated
newest added

# Patching CVE-2007-4559 Hi, we are security researchers from the Advanced Research Center at [Trellix](https://www.trellix.com). We have began a campaign to patch a widespread bug named CVE-2007-4559. CVE-2007-4559 is a...

How easy is it to generate a log of read/write access patterns and memory access inter-arrival times when running say for example a single forward pass?

memnet.How to load data to memnet model ? ``` athom@43474be86119:~/fathom$ python fathom/memnet/memnet.py /usr/local/lib/python2.7/dist-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor o f the model_selection module into which...

I am trying to run the benchmark for Alexnet via `./fathom/alexnet/alexnet.py`. But I am getting the following error: ``` Traceback (most recent call last): File "./fathom/alexnet/alexnet.py", line 137, in m...

I have just installed Fathom–including TensorFlow and other dependencies–following the [Quickstart Guide](http://fathom.readthedocs.io/en/latest/quickstart/). However, when I try to run one of the models included in Fathom– e.g. seq2seq by typing `./fathom/seq2seq/seq2seq.py`–,...

There have been some conventional advances since Fathom's release which lessen the need for things like explicit variable declarations in some of the models (e.g., convolutional networks).

M

Currently, there's only a weak need for OpenCV in DeepQ, since we don't actively visualize the emulator's behavior. Given the minor headaches associated with installing it and the rather hefty...

M

The latter is the far more common use case, and it's easy to shoot ourselves in the foot otherwise.

L

We need to make sure everything falls under an MIT-compatible license before final release. Add a master LICENSE file which comprehensively assigns credit where it is due.

M

#13 helped, but the output is still a little messy to use. Tracking a loss curve is a very useful thing, but in practice, loss isn't sufficient a lot of...

M