mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-02-12 15:45:27 -05:00
a0965ee198
* models matrix * fix typo and install gpu deps * install llvm deps if needed * fix * testops with cuda * remove pip cache since not work * cuda env * install cuda deps * maybe it will work now * i can't read * all tests in matrix * trim down more * opencl stuff in matrix * opencl pip cache * test split * change cuda test exclusion * test * fix cuda maybe * add models * add more n=auto * third thing * fix bug * cache pip more * change name * update tests * try again cause why not * balance * try again... * try apt cache for cuda * try on gpu: * try cuda again * update packages step * replace libz-dev with zlib1g-dev * only cache cuda * why error * fix gpuocelot bug * apt cache err * apt cache to slow? * opt and image in single runner * add a couple n=autos * remove test matrix * try cuda apt cache again * libz-dev -> zlib1g-dev * remove -s since not supported by xdist * the cache takes too long and doesn't work * combine webgpu and metal tests * combine imagenet to c and cpu tests * torch tests with linters * torch back by itself * small windows clang test with torch tests * fix a goofy windows bug * im dumb * bro * clang with linters * fix pylint error * linter not work on windows * try with clang again * clang and imagenet? * install deps * fix * fix quote * clang by itself (windows too slow) * env vars for imagenet * cache pip for metal and webgpu tests * try torch with metal and webgpu * doesn't work, too long * remove -v * try -n=logical * don't use logical * revert accidental thing * remove some prints unless CI * fix print unless CI * ignore speed tests for slow tests * clang windows in matrix (ubuntu being tested in imagenet->c test) * try manual pip cache * fix windows pip cache path * all manual pip cache * fix pip cache dir for macos * print_ci function in helpers * CI as variable, no print_ci * missed one * cuda tests with docker image * remove setup-python action for cuda * python->python3? * remove -s -v * try fix pip cache * maybe fix * try to fix pip cache * is this the path? * maybe cache pip * try again * create wheels dir * ? * cuda pip deps in dockerfile * disable pip cache for clang * image from ghcr instead of docker hub * why is clang like this * fast deps * try use different caches * remove the fast thing * try with lighter image * remove setup python for cuda * small docker and cuda fast deps * ignore a few more tests * cool docker thing (maybe) * oops * quotes * fix docker command * fix bug * ignore train efficientnet test * remove dockerfile (docker stuff takes too long) * remove docker stuff and normal cuda * oops * ignore the tests for cuda * does this work * ignore test_train on slow backends * add space * llvm ignore same tests as cuda * nvm * ignore lr scheduler tests * get some stats * fix ignore bug * remove extra ' * remove and * ignore test for llvm * change ignored tests and durationon all backends * fix * and -> or * ignore some more cuda tests * finally? * does this fix it * remove durations=0 * add some more tests to llvm * make last pytest more readable * fix * don't train efficientnet on cpu * try w/out pip cache * pip cache seems to be generally better * pytest file markers * try apt fast for cuda * use quick install for apt-fast * apt-fast not worth * apt-get to apt * fix typo * suppress warnings * register markers * disable debug on fuzz tests * change marker names * apt update and apt install in one command * update marker names in test.yml * webgpu pytest marker
84 lines
2.3 KiB
Python
84 lines
2.3 KiB
Python
import unittest
|
|
import time
|
|
import numpy as np
|
|
from tinygrad.state import get_parameters
|
|
from tinygrad.nn import optim
|
|
from tinygrad.tensor import Device
|
|
from tinygrad.helpers import getenv
|
|
from extra.training import train
|
|
from models.convnext import ConvNeXt
|
|
from models.efficientnet import EfficientNet
|
|
from models.transformer import Transformer
|
|
from models.vit import ViT
|
|
from models.resnet import ResNet18
|
|
import pytest
|
|
|
|
pytestmark = pytest.mark.exclude_gpu
|
|
|
|
BS = getenv("BS", 2)
|
|
|
|
def train_one_step(model,X,Y):
|
|
params = get_parameters(model)
|
|
pcount = 0
|
|
for p in params:
|
|
pcount += np.prod(p.shape)
|
|
optimizer = optim.SGD(params, lr=0.001)
|
|
print("stepping %r with %.1fM params bs %d" % (type(model), pcount/1e6, BS))
|
|
st = time.time()
|
|
train(model, X, Y, optimizer, steps=1, BS=BS)
|
|
et = time.time()-st
|
|
print("done in %.2f ms" % (et*1000.))
|
|
|
|
def check_gc():
|
|
if Device.DEFAULT == "GPU":
|
|
from extra.introspection import print_objects
|
|
assert print_objects() == 0
|
|
|
|
class TestTrain(unittest.TestCase):
|
|
def test_convnext(self):
|
|
model = ConvNeXt(depths=[1], dims=[16])
|
|
X = np.zeros((BS,3,224,224), dtype=np.float32)
|
|
Y = np.zeros((BS), dtype=np.int32)
|
|
train_one_step(model,X,Y)
|
|
check_gc()
|
|
|
|
def test_efficientnet(self):
|
|
model = EfficientNet(0)
|
|
X = np.zeros((BS,3,224,224), dtype=np.float32)
|
|
Y = np.zeros((BS), dtype=np.int32)
|
|
train_one_step(model,X,Y)
|
|
check_gc()
|
|
|
|
@unittest.skipIf(Device.DEFAULT == "WEBGPU", "too many buffers for webgpu")
|
|
def test_vit(self):
|
|
model = ViT()
|
|
X = np.zeros((BS,3,224,224), dtype=np.float32)
|
|
Y = np.zeros((BS,), dtype=np.int32)
|
|
train_one_step(model,X,Y)
|
|
check_gc()
|
|
|
|
def test_transformer(self):
|
|
# this should be small GPT-2, but the param count is wrong
|
|
# (real ff_dim is 768*4)
|
|
model = Transformer(syms=10, maxlen=6, layers=12, embed_dim=768, num_heads=12, ff_dim=768//4)
|
|
X = np.zeros((BS,6), dtype=np.float32)
|
|
Y = np.zeros((BS,6), dtype=np.int32)
|
|
train_one_step(model,X,Y)
|
|
check_gc()
|
|
|
|
def test_resnet(self):
|
|
X = np.zeros((BS, 3, 224, 224), dtype=np.float32)
|
|
Y = np.zeros((BS), dtype=np.int32)
|
|
for resnet_v in [ResNet18]:
|
|
model = resnet_v()
|
|
model.load_from_pretrained()
|
|
train_one_step(model, X, Y)
|
|
check_gc()
|
|
|
|
def test_bert(self):
|
|
# TODO: write this
|
|
pass
|
|
|
|
if __name__ == '__main__':
|
|
unittest.main()
|