github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-08 22:48:25 -05:00
Code Issues Packages Projects Releases Wiki Activity

All devices are equal! (#196)

Browse Source 
* Update all devices to be tested

ANE, CPU and OCL all now support all tests.

However tests are not currently passing on GPU and I cannot test on CPU.

Failing GPU test are not an issue caused by this update. Tests have not
been passing due to a missing "six" required installation.

OpenCL Tests have not been run since commit: 1a1c63a08b

devices have 3 types and are handle by a new DeviceTypes enum. (The goal
is to revert to Tensor.<type>, but this current setup allows for keyword
argument defaults: `device=DeviceType.CPU`)

All references to Tensor.GPU/CPU/ANE as been converted to the
corresponding `DeviceTypes` enum.

Refactor of the conversion code to allow for any device to any device
conversion.

* Add six dependency in requirements.txt

* Resolve failure to run tests

Move six into gpu required installs. Remove six from standard
installation.

* Remove repeated data conversion

* Refactor method names

Also reduce code with .to and .to_

* Dynamic device handlers

* Refactor DeviceTypes -> Device

* Add mem copy profiling back

* test_backward_pass_diamond_model passing

* Resolve Sum issue on GPU

* Revert batchnorm2d tests

* Update README with upadated API

* ANE testing with

* Last minute line gains
This commit is contained in:
Liam
2020-12-16 08:44:08 +01:00
committed by GitHub
parent 78210b5e40
commit bcf1518309
15 changed files with 246 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
extra/training.py
View File

@@ -2,21 +2,22 @@ import os
import numpy as np
from tqdm import trange
from extra.utils import get_parameters
from tinygrad.tensor import Tensor, GPU
from tinygrad.tensor import Tensor, GPU, Device
def train(model, X_train, Y_train, optim, steps, num_classes=None, BS=128, gpu=False, lossfn = lambda out,y: out.mul(y).mean()):
if gpu is True: [x.cuda_() for x in get_parameters([model, optim])]
def train(model, X_train, Y_train, optim, steps, num_classes=None, BS=128, device=Device.CPU, lossfn = lambda out,y: out.mul(y).mean()):
if device == Device.GPU: [x.gpu_() for x in get_parameters([model, optim])]
elif device == Device.ANE: [x.ane_() for x in get_parameters([model, optim])]
if num_classes is None: num_classes = Y_train.max().astype(int)+1
losses, accuracies = [], []
for i in (t := trange(steps, disable=os.getenv('CI') is not None)):
samp = np.random.randint(0, X_train.shape[0], size=(BS))
x = Tensor(X_train[samp].reshape((-1, 28*28)).astype(np.float32), gpu=gpu)
x = Tensor(X_train[samp].reshape((-1, 28*28)).astype(np.float32), device=device)
Y = Y_train[samp]
y = np.zeros((len(samp),num_classes), np.float32)
# correct loss for NLL, torch NLL loss returns one per row
y[range(y.shape[0]),Y] = -1.0*num_classes
y = Tensor(y, gpu=gpu)
y = Tensor(y, device=device)
# network
out = model.forward(x)
@@ -36,11 +37,11 @@ def train(model, X_train, Y_train, optim, steps, num_classes=None, BS=128, gpu=F
accuracies.append(accuracy)
t.set_description("loss %.2f accuracy %.2f" % (loss, accuracy))
def evaluate(model, X_test, Y_test, num_classes=None, gpu=False, BS=128):
def evaluate(model, X_test, Y_test, num_classes=None, device=Device.CPU, BS=128):
def numpy_eval(num_classes):
Y_test_preds_out = np.zeros((len(Y_test),num_classes))
for i in trange(len(Y_test)//BS, disable=os.getenv('CI') is not None):
Y_test_preds_out[i*BS:(i+1)*BS] = model.forward(Tensor(X_test[i*BS:(i+1)*BS].reshape((-1, 28*28)).astype(np.float32), gpu=gpu)).cpu().data
Y_test_preds_out[i*BS:(i+1)*BS] = model.forward(Tensor(X_test[i*BS:(i+1)*BS].reshape((-1, 28*28)).astype(np.float32), device=device)).cpu().data
Y_test_preds = np.argmax(Y_test_preds_out, axis=1)
return (Y_test == Y_test_preds).mean()