geohot/tinygrad
1
0
Fork 0
forked from tinygrad/tinygrad
Code Pull Requests Actions Activity

Update path for test_mnist in README (#706)

Browse Source
This commit is contained in:
Connor Henderson
2023-03-15 18:42:17 -07:00
committed by GitHub
parent 3a8af99adb
commit 5e8fdfa956
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -83,7 +83,7 @@ Change to `DEBUG=4` to see the generated code.
It turns out, a decent autograd tensor library is 90% of what you need for neural networks. Add an optimizer (SGD, RMSprop, and Adam implemented) from tinygrad.nn.optim, write some boilerplate minibatching code, and you have all you need.
### Neural network example (from test/test_mnist.py)
### Neural network example (from test/models/test_mnist.py)
```python
from tinygrad.tensor import Tensor
@@ -227,7 +227,7 @@ tinygrad will always be below 1000 lines. If it isn't, we will revert commits un
* Purple edge is intermediates created in the forward
```bash
GRAPH=1 python3 test/test_mnist.py TestMNIST.test_sgd_onestep
GRAPH=1 python3 test/models/test_mnist.py TestMNIST.test_sgd_onestep
# requires dot, outputs /tmp/net.svg
```