braindevices · June 30, 2024 01:05 · Jun 30, 2024 · Jun 30, 2024 · Jun 30, 2024 · Jun 30, 2024
diff --git a/cal_yolov8_rf.py b/cal_yolov8_rf.py
@@ -31,6 +31,12 @@
     btn*1 # bottom-up C2f 3*d
 ]
 
+blocks_dets = [
+    _b + [
+      [(3,1)]*2
+    ]
+    for _b in [blocks_P3, blocks_P4, blocks_P5]
+]
 
 rfs_Cs = get_feature_node_RF(blocks, idx_Cs)
 for i, rf in enumerate(rfs_Cs):
@@ -40,4 +46,8 @@
 rf_P4 = get_feature_node_RF(blocks_P4, [len(blocks_P4)-1])[-1]
 rf_P5 = get_feature_node_RF(blocks_P5, [len(blocks_P5)-1])[-1]
 for i, rf in enumerate([rf_P3, rf_P4, rf_P5]):
-    print(f"P{i+3} has RF= {rf}x{rf}")
+    print(f"P{i+3} has RF= {rf}x{rf}")
+
+for i, _b in enumerate(blocks_dets):
+    rf = get_feature_node_RF(_b, [len(_b)-1])[-1]
+    print(f"DET_P{i+3} has RF= {rf}x{rf}")
diff --git a/cal_yolov8_rf.py b/cal_yolov8_rf.py
@@ -1,5 +1,5 @@
-# each bottleneck blcok has 3 conv that k>1
-btn = [(3,1)]*3
+# each bottleneck blcok has 4 conv that k>1
+btn = [(3,1)]*4
 # stem, C1 (1), C2 (2), conv, C3 (4), conv, C4 (6), conv, C2f, C5 (SPPF) (9)
 idx_Cs = [1,2,4,6,9]
 blocks = [

diff --git a/cal_yolov8_rf.py b/cal_yolov8_rf.py
@@ -0,0 +1,43 @@
+# each bottleneck blcok has 3 conv that k>1
+btn = [(3,1)]*3
+# stem, C1 (1), C2 (2), conv, C3 (4), conv, C4 (6), conv, C2f, C5 (SPPF) (9)
+idx_Cs = [1,2,4,6,9]
+blocks = [
+  [(3,2)], # conv
+  [(3,2)], # conv
+  btn*1, # C2f n=3*d
+  [(3,2)], # conv
+  btn*2, # C2f n=6*d
+  [(3,2)],
+  btn*2, # C2f n=6*d
+  [(3,2)],
+  btn*1, # C2f n=3*d
+  [(3,1), (5,1), (5,1), (5,1), (3, 1)] # SPPF
+]
+
+blocks_P3 = blocks + [
+  btn*1, # top-down C2f 3*d
+  btn*1 # top-down C2f 3*d
+]
+blocks_P4 = blocks_P3 + [
+  [
+    (3,2)], # bottom up Conv
+    btn*1 # bottom-up C2f 3*d
+]
+
+blocks_P5 = blocks_P4 + [
+  [
+    (3,2)], # bottom up Conv
+    btn*1 # bottom-up C2f 3*d
+]
+
+
+rfs_Cs = get_feature_node_RF(blocks, idx_Cs)
+for i, rf in enumerate(rfs_Cs):
+    print(f"C{i+1} has RF= {rf}x{rf}")
+
+rf_P3 = get_feature_node_RF(blocks_P3, [len(blocks_P3)-1])[-1]
+rf_P4 = get_feature_node_RF(blocks_P4, [len(blocks_P4)-1])[-1]
+rf_P5 = get_feature_node_RF(blocks_P5, [len(blocks_P5)-1])[-1]
+for i, rf in enumerate([rf_P3, rf_P4, rf_P5]):
+    print(f"P{i+3} has RF= {rf}x{rf}")
diff --git a/receptive_field.py b/receptive_field.py
@@ -0,0 +1,33 @@
+def calculate_receptive_fields(layers):
+    """
+    Calculate the receptive field for each layer given a list of (kernel size, stride) tuples.
+    
+    Parameters:
+        layers (list of tuples): Each tuple contains (kernel size, stride) for a layer.
+        
+    Returns:
+        list: Receptive field for each layer.
+    """
+    receptive_fields = []
+    receptive_field = 1  # The initial receptive field for the first layer
+
+    for i, (kernel_size, stride) in enumerate(layers):
+        if i == 0:
+            receptive_field = kernel_size
+        else:
+            receptive_field += (kernel_size - 1) * stride
+        receptive_fields.append(receptive_field)
+
+    return receptive_fields
+
+from itertools import chain
+from typing import List, List, Tuple
+import torch
+def get_feature_node_RF(blocks: List[List[Tuple[int, int]]], idxs_feature_node: List[int]):
+    lens_block = [len(l) for l in blocks]
+    idxs_block_out_layer = torch.cumsum(torch.tensor(lens_block), -1)-1
+    idxs_layer_ft = idxs_block_out_layer[idxs_feature_node]
+    layers_flatten = list(chain.from_iterable(blocks))
+    rfs = calculate_receptive_fields(layers_flatten)
+    return torch.tensor(rfs)[idxs_layer_ft]
+
No results found