From 0e4fd5c573031b875bb10aaef6157b2db5671fbf Mon Sep 17 00:00:00 2001
From: Francis Lata <francisalbertlata@gmail.com>
Date: Mon, 23 Dec 2024 05:16:13 +0000
Subject: [PATCH] revert helper changes

---
 extra/models/helpers.py   | 23 -----------------------
 extra/models/retinanet.py | 17 ++++++++++++++++-
 2 files changed, 16 insertions(+), 24 deletions(-)
 delete mode 100644 extra/models/helpers.py

diff --git a/extra/models/helpers.py b/extra/models/helpers.py
deleted file mode 100644
index a3b0c565fb..0000000000
--- a/extra/models/helpers.py
+++ /dev/null
@@ -1,23 +0,0 @@
-import numpy as np
-from tinygrad import Tensor
-
-def nms(boxes, scores, thresh=0.5):
-  x1, y1, x2, y2 = np.rollaxis(boxes, 1)
-  areas = (x2 - x1 + 1) * (y2 - y1 + 1)
-  to_process, keep = scores.argsort()[::-1], []
-  while to_process.size > 0:
-    cur, to_process = to_process[0], to_process[1:]
-    keep.append(cur)
-    inter_x1 = np.maximum(x1[cur], x1[to_process])
-    inter_y1 = np.maximum(y1[cur], y1[to_process])
-    inter_x2 = np.minimum(x2[cur], x2[to_process])
-    inter_y2 = np.minimum(y2[cur], y2[to_process])
-    inter_area = np.maximum(0, inter_x2 - inter_x1 + 1) * np.maximum(0, inter_y2 - inter_y1 + 1)
-    iou = inter_area / (areas[cur] + areas[to_process] - inter_area)
-    to_process = to_process[np.where(iou <= thresh)[0]]
-  return keep
-
-def meshgrid(x, y):
-  grid_x = Tensor.cat(*[x[idx:idx+1].expand(y.shape).unsqueeze(0) for idx in range(x.shape[0])])
-  grid_y = Tensor.cat(*[y.unsqueeze(0)]*x.shape[0])
-  return grid_x.reshape(-1, 1), grid_y.reshape(-1, 1)
diff --git a/extra/models/retinanet.py b/extra/models/retinanet.py
index 4cac85a297..68bfd39f02 100644
--- a/extra/models/retinanet.py
+++ b/extra/models/retinanet.py
@@ -7,11 +7,26 @@ import tinygrad.nn as nn
 from examples.mlperf.helpers import generate_anchors
 from examples.mlperf.initializers import Conv2dNormal, Conv2dKaimingUniform
 from examples.mlperf.losses import sigmoid_focal_loss, l1_loss
-from extra.models.helpers import nms
 from extra.models.resnet import ResNet
 from extra.models.mask_rcnn import BoxCoder
 import numpy as np
 
+def nms(boxes, scores, thresh=0.5):
+  x1, y1, x2, y2 = np.rollaxis(boxes, 1)
+  areas = (x2 - x1 + 1) * (y2 - y1 + 1)
+  to_process, keep = scores.argsort()[::-1], []
+  while to_process.size > 0:
+    cur, to_process = to_process[0], to_process[1:]
+    keep.append(cur)
+    inter_x1 = np.maximum(x1[cur], x1[to_process])
+    inter_y1 = np.maximum(y1[cur], y1[to_process])
+    inter_x2 = np.minimum(x2[cur], x2[to_process])
+    inter_y2 = np.minimum(y2[cur], y2[to_process])
+    inter_area = np.maximum(0, inter_x2 - inter_x1 + 1) * np.maximum(0, inter_y2 - inter_y1 + 1)
+    iou = inter_area / (areas[cur] + areas[to_process] - inter_area)
+    to_process = to_process[np.where(iou <= thresh)[0]]
+  return keep
+
 def decode_bbox(offsets, anchors):
   dx, dy, dw, dh = np.rollaxis(offsets, 1)
   widths, heights = anchors[:, 2] - anchors[:, 0], anchors[:, 3] - anchors[:, 1]