"""Build optimized ONNX model for Task 028. Rule (265/265 verified): 1. Input is 10x10 with exactly 2 colored dots on a bg of 0 2. Upper dot (closer to row 0) → fills upper zone with its color 3. Lower dot (closer to row 9) → fills lower zone with its color 4. Each zone pattern: full row at dot position, full row at border (0 or 9), columns 0 and 9 filled in between. Interior stays 0. 5. Boundary between zones is midpoint of the two dot rows. ONNX approach: - Slice to 10x10 - Detect non-bg channels, find dot row positions via ArgMax on row sums - Generate masks using row/col grids and comparisons - Combine with color one-hots - Pad back to 30x30 Base: 10 nodes, 12610 params, score 12.83 Target: ~40 nodes, ~1500 params → score ~15+ (gain +2.5) """ import sys, os sys.path.insert(0, '/app/repo/medal-solvers') sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) from onnx import TensorProto import numpy as np import onnx from onnx import helper, numpy_helper import math def build_task028(): nodes, inits, vis = [], [], [] counter = [0] def nm(): counter[0] += 1 return f"t{counter[0]}" def const(name, val, dtype='f'): arr = np.array(val, dtype=np.float32 if dtype == 'f' else np.int64) inits.append(numpy_helper.from_array(arr, name)) def vi(name, shape, dt=TensorProto.FLOAT): vis.append(helper.make_tensor_value_info(name, dt, shape)) def nd(op, ins, outs_shapes, **kwargs): out_names = [] for sd in outs_shapes: if isinstance(sd, tuple): shape, dt = sd else: shape, dt = sd, TensorProto.FLOAT n = nm() vi(n, shape, dt) out_names.append(n) nodes.append(helper.make_node(op, ins, out_names, **kwargs)) return out_names[0] if len(out_names) == 1 else out_names # === CONSTANTS === const('c_half', [0.5]) const('c_one', [1.0]) const('c_zero', [0.0]) const('c_two', [2.0]) const('c_9f', [9.0]) const('sl_start', [0, 0, 0, 0], 'i') const('sl_end', [1, 10, 10, 10], 'i') const('sl_axes', [0, 1, 2, 3], 'i') const('axes3', [3], 'i') # cols const('axes23', [2, 3], 'i') const('axes1', [1], 'i') # Row grid [1,1,10,1] - row index values const('row_grid', np.arange(10, dtype=np.float32).reshape(1, 1, 10, 1)) # Col grid [1,1,1,10] const('col_grid', np.arange(10, dtype=np.float32).reshape(1, 1, 1, 10)) const('shape_1_1_1_1', [1, 1, 1, 1], 'i') const('shape_1_10_1_1', [1, 10, 1, 1], 'i') const('depth_10', [10.0]) const('oh_vals', [0.0, 1.0]) # Pad to get back to 30x30 const('pad_10_to_30', [0, 0, 0, 0, 0, 0, 20, 20], 'i') const('pad_val_zero', [0.0]) # Indices const('idx_0', [0], 'i') const('idx_1', [1], 'i') const('idx_bg', [0], 'i') # Slice to get non-bg channels [1, 9, 10, 10] const('sl_ch_start', [0, 1, 0, 0], 'i') const('sl_ch_end', [1, 10, 10, 10], 'i') # === STEP 1: Slice input to 10x10 === inp10 = nd('Slice', ['input', 'sl_start', 'sl_end', 'sl_axes'], [[1, 10, 10, 10]]) # === STEP 2: Find the two dots === # Sum non-bg channels to get overall non-zero mask [1,1,10,10] nonbg = nd('Slice', [inp10, 'sl_ch_start', 'sl_ch_end', 'sl_axes'], [[1, 9, 10, 10]]) active = nd('ReduceSum', [nonbg, 'axes1'], [[1, 1, 10, 10]], keepdims=1) # Sum per row to find which rows have dots [1,1,10,1] row_sums = nd('ReduceSum', [active, 'axes3'], [[1, 1, 10, 1]], keepdims=1) # Find the two dot rows: first dot = ArgMax of row_sums # But we have 2 dots. Use: first non-zero row from top = upper dot # For upper dot: row_sums * row_grid gives weighted; we want min non-zero row # Trick: add large value where row_sum==0, then ArgMin const('c_big', [100.0]) has_dot_b = nd('Greater', [row_sums, 'c_half'], [([1, 1, 10, 1], TensorProto.BOOL)]) has_dot = nd('Cast', [has_dot_b], [[1, 1, 10, 1]], to=1) no_dot = nd('Sub', ['c_one', has_dot], [[1, 1, 10, 1]]) # For upper dot (minimum row with a dot): row_masked_upper = nd('Add', [nd('Mul', ['row_grid', has_dot], [[1, 1, 10, 1]]), nd('Mul', ['c_big', no_dot], [[1, 1, 10, 1]])], [[1, 1, 10, 1]]) const('axes2', [2], 'i') upper_row_idx = nd('ArgMin', [row_masked_upper], [([1, 1, 1, 1], TensorProto.INT64)], axis=2, keepdims=1) upper_row_f = nd('Cast', [upper_row_idx], [[1, 1, 1, 1]], to=1) # For lower dot (maximum row with a dot): row_masked_lower = nd('Mul', ['row_grid', has_dot], [[1, 1, 10, 1]]) lower_row_idx = nd('ArgMax', [row_masked_lower], [([1, 1, 1, 1], TensorProto.INT64)], axis=2, keepdims=1) lower_row_f = nd('Cast', [lower_row_idx], [[1, 1, 1, 1]], to=1) # Midpoint between dots sum_rows = nd('Add', [upper_row_f, lower_row_f], [[1, 1, 1, 1]]) mid_row = nd('Div', [sum_rows, 'c_two'], [[1, 1, 1, 1]]) # === STEP 3: Find dot colors === # Channel sums per row: for upper dot's row, which channel has the dot? # Gather the input at upper_row → [1, 10, 1, 10] then sum over cols → [1, 10, 1, 1] # Simpler: total channel sums weighted by position # Upper dot color: extract channels at upper dot row # Use: for each channel, check if it has a 1 at the upper dot row # channel_at_upper[c] = sum over cols of inp10[0, c, upper_row, :] # Since there's exactly one dot per row, the channel with max sum IS the color # Sum each channel over all spatial positions → [1, 10, 1, 1] # This gives total pixel count per channel. But we have 2 dots of possibly different colors. # Instead: create mask for upper zone and lower zone, then find color per zone. # Upper zone mask: rows <= mid_row [1,1,10,1] in_upper_b = nd('Less', ['row_grid', nd('Add', [mid_row, 'c_half'], [[1, 1, 1, 1]])], [([1, 1, 10, 1], TensorProto.BOOL)]) in_upper = nd('Cast', [in_upper_b], [[1, 1, 10, 1]], to=1) # [1,1,10,1] in_lower = nd('Sub', ['c_one', in_upper], [[1, 1, 10, 1]]) # Upper color: which channel has pixels in the upper zone? # Mask input by upper zone: inp10 * in_upper [1,10,10,10] * [1,1,10,1] → [1,10,10,10] upper_masked = nd('Mul', [inp10, in_upper], [[1, 10, 10, 10]]) upper_ch_sums = nd('ReduceSum', [upper_masked, 'axes23'], [[1, 10, 1, 1]], keepdims=1) # Skip channel 0 (bg) const('bg_mask_10', np.array([[[[0, 1, 1, 1, 1, 1, 1, 1, 1, 1]]]], dtype=np.float32).reshape(1, 10, 1, 1)) upper_ch_masked = nd('Mul', [upper_ch_sums, 'bg_mask_10'], [[1, 10, 1, 1]]) upper_color_idx = nd('ArgMax', [upper_ch_masked], [([1, 1, 1, 1], TensorProto.INT64)], axis=1, keepdims=1) upper_color_1d = nd('Reshape', [upper_color_idx, 'idx_1'], [([1], TensorProto.INT64)]) # Lower color lower_masked = nd('Mul', [inp10, in_lower], [[1, 10, 10, 10]]) lower_ch_sums = nd('ReduceSum', [lower_masked, 'axes23'], [[1, 10, 1, 1]], keepdims=1) lower_ch_masked = nd('Mul', [lower_ch_sums, 'bg_mask_10'], [[1, 10, 1, 1]]) lower_color_idx = nd('ArgMax', [lower_ch_masked], [([1, 1, 1, 1], TensorProto.INT64)], axis=1, keepdims=1) lower_color_1d = nd('Reshape', [lower_color_idx, 'idx_1'], [([1], TensorProto.INT64)]) # === STEP 4: Build output masks === # Upper zone pattern [1,1,10,10]: # Full row at row 0, full row at upper_dot_row, cols 0&9 in between const('c_0f', [0.0]) # Row == 0 at_row0_b = nd('Less', ['row_grid', 'c_half'], [([1, 1, 10, 1], TensorProto.BOOL)]) at_row0 = nd('Cast', [at_row0_b], [[1, 1, 10, 1]], to=1) # Row == upper_dot_row diff_upper = nd('Abs', [nd('Sub', ['row_grid', upper_row_f], [[1, 1, 10, 1]])], [[1, 1, 10, 1]]) at_upper_b = nd('Less', [diff_upper, 'c_half'], [([1, 1, 10, 1], TensorProto.BOOL)]) at_upper = nd('Cast', [at_upper_b], [[1, 1, 10, 1]], to=1) # Full rows in upper zone: row 0 OR dot row full_upper_rows = nd('Max', [at_row0, at_upper], [[1, 1, 10, 1]]) # Edge cols: col==0 or col==9 const('c_8_5', [8.5]) at_col0_b = nd('Less', ['col_grid', 'c_half'], [([1, 1, 1, 10], TensorProto.BOOL)]) at_col0 = nd('Cast', [at_col0_b], [[1, 1, 1, 10]], to=1) at_col9_b = nd('Greater', ['col_grid', 'c_8_5'], [([1, 1, 1, 10], TensorProto.BOOL)]) at_col9 = nd('Cast', [at_col9_b], [[1, 1, 1, 10]], to=1) edge_cols = nd('Max', [at_col0, at_col9], [[1, 1, 1, 10]]) # Upper mask: (full_rows broadcast to 10x10) OR (edge_cols * in_upper_zone) # full_rows [1,1,10,1] → broadcast with ones [1,1,1,10] → [1,1,10,10] # But in ONNX: Max already broadcasts upper_full = full_upper_rows # [1,1,10,1] will broadcast upper_edges = nd('Mul', [edge_cols, in_upper], [[1, 1, 10, 10]]) # [1,1,1,10]*[1,1,10,1]→[1,1,10,10] upper_mask_raw = nd('Max', [upper_full, upper_edges], [[1, 1, 10, 10]]) upper_mask = nd('Mul', [upper_mask_raw, in_upper], [[1, 1, 10, 10]]) # clip to upper zone # Lower zone pattern: # Full row at row 9, full row at lower_dot_row, cols 0&9 in between at_row9_b = nd('Greater', ['row_grid', 'c_8_5'], [([1, 1, 10, 1], TensorProto.BOOL)]) at_row9 = nd('Cast', [at_row9_b], [[1, 1, 10, 1]], to=1) diff_lower = nd('Abs', [nd('Sub', ['row_grid', lower_row_f], [[1, 1, 10, 1]])], [[1, 1, 10, 1]]) at_lower_b = nd('Less', [diff_lower, 'c_half'], [([1, 1, 10, 1], TensorProto.BOOL)]) at_lower = nd('Cast', [at_lower_b], [[1, 1, 10, 1]], to=1) full_lower_rows = nd('Max', [at_row9, at_lower], [[1, 1, 10, 1]]) lower_full = full_lower_rows lower_edges = nd('Mul', [edge_cols, in_lower], [[1, 1, 10, 10]]) lower_mask_raw = nd('Max', [lower_full, lower_edges], [[1, 1, 10, 10]]) lower_mask = nd('Mul', [lower_mask_raw, in_lower], [[1, 1, 10, 10]]) # === STEP 5: Apply colors === # Upper color one-hot [1, 10, 1, 1] upper_oh = nd('OneHot', [upper_color_1d, 'depth_10', 'oh_vals'], [[1, 10]], axis=1) upper_oh_4d = nd('Reshape', [upper_oh, 'shape_1_10_1_1'], [[1, 10, 1, 1]]) upper_out = nd('Mul', [upper_oh_4d, upper_mask], [[1, 10, 10, 10]]) # Lower color one-hot [1, 10, 1, 1] lower_oh = nd('OneHot', [lower_color_1d, 'depth_10', 'oh_vals'], [[1, 10]], axis=1) lower_oh_4d = nd('Reshape', [lower_oh, 'shape_1_10_1_1'], [[1, 10, 1, 1]]) lower_out = nd('Mul', [lower_oh_4d, lower_mask], [[1, 10, 10, 10]]) # Combine colored channels colored_10 = nd('Add', [upper_out, lower_out], [[1, 10, 10, 10]]) # === STEP 6: Add background channel === # ch0 = 1 where no other channel is active (inside 10x10) # Slice channels 1-9, take max, subtract from 1 nonbg_10 = nd('Slice', [colored_10, 'sl_ch_start', 'sl_ch_end', 'sl_axes'], [[1, 9, 10, 10]]) any_color = nd('ReduceMax', [nonbg_10, 'axes1'], [[1, 1, 10, 10]], keepdims=1) bg_ch = nd('Sub', ['c_one', any_color], [[1, 1, 10, 10]]) # Build ch0 one-hot and add const('ch0_idx', [0], 'i') ch0_oh = nd('OneHot', ['ch0_idx', 'depth_10', 'oh_vals'], [[1, 10]], axis=1) ch0_oh_4d = nd('Reshape', [ch0_oh, 'shape_1_10_1_1'], [[1, 10, 1, 1]]) bg_full = nd('Mul', [ch0_oh_4d, bg_ch], [[1, 10, 10, 10]]) out_10 = nd('Add', [colored_10, bg_full], [[1, 10, 10, 10]]) # === STEP 7: Pad to 30x30 === final = nd('Pad', [out_10, 'pad_10_to_30', 'pad_val_zero'], [[1, 10, 30, 30]]) # Build model x = helper.make_tensor_value_info('input', TensorProto.FLOAT, [1, 10, 30, 30]) y = helper.make_tensor_value_info('output', TensorProto.FLOAT, [1, 10, 30, 30]) nodes.append(helper.make_node('Identity', [final], ['output'])) graph = helper.make_graph(nodes, 'task028', [x], [y], initializer=inits, value_info=vis) model = helper.make_model(graph, ir_version=10, opset_imports=[helper.make_opsetid('', 18)]) return model if __name__ == '__main__': import onnxruntime as ort import json from huggingface_hub import hf_hub_download import zipfile print("Building Task 028 ONNX model...") model = build_task028() output_path = '/app/task028.onnx' onnx.save(model, output_path) fsize = os.path.getsize(output_path) print(f" Nodes: {len(model.graph.node)}") print(f" File size: {fsize:,} bytes") # Validate sess = ort.InferenceSession(output_path) task_path = hf_hub_download('rogermt/neurogolf-solver', 'own-solver/neurogolf-2026.zip') with zipfile.ZipFile(task_path, 'r') as zf: data = json.loads(zf.read('task028.json')) all_examples = data['train'] + data['test'] + data.get('arc-gen', []) right_count, wrong_count = 0, 0 for i, ex in enumerate(all_examples): inp_grid = ex['input'] inp = np.zeros((1, 10, 30, 30), dtype=np.float32) for r, row in enumerate(inp_grid): for c, v in enumerate(row): if r < 30 and c < 30: inp[0][v][r][c] = 1.0 result = sess.run(['output'], {'input': inp}) out = (result[0] > 0.0).astype(float) exp = np.zeros((1, 10, 30, 30), dtype=np.float32) for r, row in enumerate(ex['output']): for c, v in enumerate(row): if r < 30 and c < 30: exp[0][v][r][c] = 1.0 if np.array_equal(out, exp): right_count += 1 else: wrong_count += 1 if wrong_count <= 3: diff_locs = np.where(out != exp) print(f" FAIL {i}: {len(diff_locs[0])} diffs") print(f"\nResults: {right_count} pass, {wrong_count} fail out of {len(all_examples)}") if wrong_count == 0: # Score estimate params = sum(int(np.prod(init.dims)) for init in model.graph.initializer) mem_est = sum(int(np.prod([d.dim_value for d in vi.type.tensor_type.shape.dim])) * 4 for vi in model.graph.value_info if vi.type.HasField('tensor_type') and vi.type.tensor_type.HasField('shape')) score_est = max(1.0, 25.0 - math.log(max(1.0, mem_est + params))) print(f" Params: {params:,}, Memory est: {mem_est:,}") print(f" Score est: {score_est:.3f} (base: 12.831)") print(f" Gain est: +{score_est - 12.831:.3f}")