readme updates

This commit is contained in:
George Hotz
2020-11-02 08:30:43 -08:00
parent f178d23ff3
commit 1e6bbdf4f8

View File

@@ -12,6 +12,8 @@ This may not be the best deep learning framework, but it is a deep learning fram
The Tensor class is a wrapper around a numpy array, except it does Tensor things.
Update: tinygrad also somewhat supports GPUs through pyopencl. Our end goal is to train an ImageNet EfficientNet-B0.
### Installation
```bash
@@ -76,6 +78,12 @@ loss.backward()
optim.step()
```
### ImageNet inference (on the micrograd puppy)
```bash
python3 examples/examples/efficientnet.py
```
### The promise of small
tinygrad will always be below 1000 lines. If it isn't, we will revert commits until tinygrad becomes smaller.