pierreandLetta Code
a2ff07234c
acc was seeded with @splat(bias) and reduced with .Add, so every linear output carried 7 extra copies of its bias. conv2d was unaffected (bias via memset), which is why the trunk matched zig-solver to 5e-6 while fc/head activations diverged — the 81% labels regression. Also adds a scalar tail for in_n < 8 (pose_fc has in_n=4) and a known-answer selftest (test_linear). 👾 Generated with [Letta Code](https://letta.com) Co-Authored-By: Letta Code <noreply@letta.com>
30 lines
985 B
Zig
30 lines
985 B
Zig
//! Minimal known-answer test for layers.linear.
|
|
const std = @import("std");
|
|
const crucible = @import("crucible");
|
|
|
|
pub fn main(init: std.process.Init) !void {
|
|
const alloc = init.gpa;
|
|
|
|
// in_n = 8, out_n = 1, bias 0. w = 1..8, x = 1..8 -> expect 204.
|
|
var w: [8]f32 = .{ 1, 2, 3, 4, 5, 6, 7, 8 };
|
|
var x: [8]f32 = .{ 1, 2, 3, 4, 5, 6, 7, 8 };
|
|
var b: [1]f32 = .{0};
|
|
var out: [1]f32 = undefined;
|
|
crucible.layers.linear(&x, &w, &b, &out);
|
|
std.debug.print("case1 (expect 204): {e}\n", .{out[0]});
|
|
|
|
// bias 100
|
|
b[0] = 100;
|
|
crucible.layers.linear(&x, &w, &b, &out);
|
|
std.debug.print("case2 (expect 304): {e}\n", .{out[0]});
|
|
|
|
// in_n = 4 (the pose_fc case!) w=1..4 x=1..4 -> 30
|
|
var w4: [4]f32 = .{ 1, 2, 3, 4 };
|
|
var x4: [4]f32 = .{ 1, 2, 3, 4 };
|
|
var b1: [1]f32 = .{0};
|
|
var out1: [1]f32 = undefined;
|
|
crucible.layers.linear(&x4, &w4, &b1, &out1);
|
|
std.debug.print("case3 (expect 30): {e}\n", .{out1[0]});
|
|
_ = alloc;
|
|
}
|