def test_tinygrad():
u = Tensor(U_init, device=self.device)
v = Tensor(V_init, device=self.device)
w = Tensor(W_init, device=self.device)
x = u.mul(v).relu()
y = u.mul(w).relu()
out = x.add(y).mul(y).relu()
out = out.logsoftmax()
out = out.sum()
out.backward()
return out.cpu().data, u.cpu().grad.data, v.cpu().grad.data, w.cpu(
).grad.data
def forward(self, x):
modules = self.blocks[1:]
outputs = {} # Cached outputs for route layer
write = 0
for i, module in enumerate(modules):
module_type = (module["type"])
st = time.time()
if module_type == "convolutional" or module_type == "upsample":
for index, layer in enumerate(self.module_list[i]):
x = layer(x)
elif module_type == "route":
layers = module["layers"]
layers = [int(a) for a in layers]
if (layers[0]) > 0:
layers[0] = layers[0] - i
if len(layers) == 1:
x = outputs[i + (layers[0])]
else:
if (layers[1]) > 0: layers[1] = layers[1] - i
map1 = outputs[i + layers[0]]
map2 = outputs[i + layers[1]]
x = Tensor(
np.concatenate((map1.cpu().data, map2.cpu().data), 1))
elif module_type == "shortcut":
from_ = int(module["from"])
x = outputs[i - 1] + outputs[i + from_]
elif module_type == "yolo":
anchors = self.module_list[i][0].anchors
inp_dim = int(self.net_info["height"])
# inp_dim = 416
num_classes = int(module["classes"])
# Transform
x = predict_transform(x, inp_dim, anchors, num_classes)
if not write:
detections = x
write = 1
else:
detections = Tensor(
np.concatenate((detections.cpu().data, x.cpu().data),
1))
# print(module_type, 'layer took %.2f s' % (time.time() - st))
outputs[i] = x
return detections # Return detections
def backward(ctx, grad_output):
in_shape, = ctx.saved_tensors
return MetalBuffer(in_shape, grad_output)
# METAL=1 python3 test/test_ops.py TestOps.test_relu
if __name__ == "__main__":
b1 = MetalBuffer(10, np.ones(10))
b2 = MetalBuffer(10, np.ones(10))
out = MetalBuffer(10, None)
mtl_buffer = cmd_buffer()
add_shader.encodeToCommandBuffer_primaryTexture_secondaryTexture_destinationTexture_(
mtl_buffer, b1.texture, b2.texture, out.texture)
mtl_buffer.commit()
print(b1.toCPU())
print(b2.toCPU())
print(out.toCPU())
from tinygrad.tensor import Tensor, Device
r1 = Tensor([-2, -1, 0, 2, 4], device=Device.METAL)
r2 = r1.relu()
r3 = r2.sum()
r3.backward()
print(r1.cpu())
print(r2.cpu())
print(r3.cpu())
#!/usr/bin/env python3 import numpy as np from tinygrad.tensor import Tensor a = Tensor([-2, -1, 0, 1, 2]).ane() print(a.cpu()) b = a.relu() print(b.cpu())
