test_topi_conv2d_hwcn.py 2.61 KB
Newer Older
1 2 3 4 5
"""Example code to do convolution."""
import os
import numpy as np
import tvm
import topi
6
import topi.testing
7
from tvm.contrib.pickle_memoize import memoize
8
from topi.util import get_const_tuple
9 10


11
def verify_conv2d_hwcn(batch, in_channel, in_size, num_filter, kernel, stride, padding, dilation=1):
12 13 14 15
    in_height = in_width = in_size

    A = tvm.placeholder((in_height, in_width, in_channel, batch), name='A')
    W = tvm.placeholder((kernel, kernel, in_channel, num_filter), name='W')
16
    B = topi.nn.conv2d_hwcn(A, W, stride, padding, dilation)
17
    C = topi.nn.relu(B)
18 19
    s1 = topi.cuda.schedule_conv2d_hwcn([B])
    s2 = topi.cuda.schedule_conv2d_hwcn([C])
20

21 22 23 24 25 26 27 28
    a_shape = get_const_tuple(A.shape)
    w_shape = get_const_tuple(W.shape)
    dtype = A.dtype

    @memoize("topi.tests.test_topi_conv2d_hwcn.verify_hwcn")
    def get_ref_data():
        a_np = np.random.uniform(size=a_shape).astype(dtype)
        w_np = np.random.uniform(size=w_shape).astype(dtype)
29 30
        dw_np = topi.testing.dilate_python(w_np, (dilation, dilation, 1, 1))
        b_np = topi.testing.conv2d_hwcn_python(a_np, dw_np, stride, padding)
31 32 33
        c_np = np.maximum(b_np, 0)
        return a_np, w_np, b_np, c_np
    a_np, w_np, b_np, c_np = get_ref_data()
34 35

    def check_device(device):
36 37
        ctx = tvm.context(device, 0)
        if not ctx.exist:
38 39
            print("Skip because %s is not enabled" % device)
            return
40
        print("Running on target: %s" % device)
41 42 43 44
        a = tvm.nd.array(a_np, ctx)
        w = tvm.nd.array(w_np, ctx)
        b = tvm.nd.array(np.zeros(get_const_tuple(B.shape), dtype=B.dtype), ctx)
        c = tvm.nd.array(np.zeros(get_const_tuple(C.shape), dtype=C.dtype), ctx)
45 46 47 48
        func1 = tvm.build(s1, [A, W, B], device)
        func2 = tvm.build(s2, [A, W, C], device)
        func1(a, w, b)
        func2(a, w, c)
49 50
        tvm.testing.assert_allclose(b.asnumpy(), b_np, rtol=1e-5)
        tvm.testing.assert_allclose(c.asnumpy(), c_np, rtol=1e-5)
51

52
    for device in ['cuda', 'opencl', 'metal', 'rocm', 'vulkan', 'nvptx']:
53 54 55
        check_device(device)


56 57 58 59 60 61 62 63 64
def test_conv2d_hwcn():
    verify_conv2d_hwcn(1, 256, 32, 256, 3, 1, "SAME")
    verify_conv2d_hwcn(1, 256, 32, 256, 3, 1, "SAME")
    verify_conv2d_hwcn(4, 128, 16, 128, 5, 2, "SAME")
    verify_conv2d_hwcn(4, 128, 16, 256, 5, 2, "SAME")
    verify_conv2d_hwcn(1, 256, 32, 256, 3, 1, "VALID")
    verify_conv2d_hwcn(1, 256, 32, 256, 3, 1, "VALID")
    verify_conv2d_hwcn(4, 128, 16, 128, 5, 2, "VALID")
    verify_conv2d_hwcn(4, 128, 16, 256, 5, 2, "VALID")
65 66
    # dilation = 2
    verify_conv2d_hwcn(1, 256, 32, 256, 3, 1, "SAME", dilation=2)
67 68

if __name__ == "__main__":
69
    test_conv2d_hwcn()