Pārlūkot izejas kodu

Fix TFDWConv() `c1 == c2` check (#7842)

modifyDataloader
Glenn Jocher GitHub pirms 2 gadiem
vecāks
revīzija
2b64b45cd8
Šim parakstam datu bāzē netika atrasta zināma atslēga GPG atslēgas ID: 4AEE18F83AFDEB23
1 mainītis faili ar 2 papildinājumiem un 2 dzēšanām
  1. +2
    -2
      models/tf.py

+ 2
- 2
models/tf.py Parādīt failu

@@ -88,10 +88,10 @@ class TFConv(keras.layers.Layer):

class TFDWConv(keras.layers.Layer):
# Depthwise convolution
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
def __init__(self, c1, c2, k=1, s=1, p=None, act=True, w=None):
# ch_in, ch_out, weights, kernel, stride, padding, groups
super().__init__()
assert g == c1 == c2, f'TFDWConv() groups={g} must equal input={c1} and output={c2} channels'
assert c1 == c2, f'TFDWConv() input={c1} must equal output={c2} channels'
conv = keras.layers.DepthwiseConv2D(
kernel_size=k,
strides=s,

Notiek ielāde…
Atcelt
Saglabāt