From 88a27ef3d515dd311f604d0292bed6be1f77f1d8 Mon Sep 17 00:00:00 2001
From: kongdebug <52785738+kongdebug@users.noreply.github.com>
Date: Thu, 28 Apr 2022 13:10:11 +0800
Subject: [PATCH] [fix] fix a little bug of Bit model exporting (#64)

---
 deploy/export/README.md          | 1 +
 paddlers/custom_models/cd/bit.py | 8 ++++----
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/deploy/export/README.md b/deploy/export/README.md
index 6cf86df..ae8e7d3 100644
--- a/deploy/export/README.md
+++ b/deploy/export/README.md
@@ -60,3 +60,4 @@ python deploy/export_model.py --model_dir=./output/deeplabv3p/best_model/ --save
 - 对于检测模型中的YOLO/PPYOLO系列模型，请保证输入影像的`w`和`h`有相同取值、且均为32的倍数；指定`--fixed_input_shape`时，R-CNN模型的`w`和`h`也均需为32的倍数。
 - 指定`[w,h]`时，请使用半角逗号（`,`）分隔`w`和`h`，二者之间不允许存在空格等其它字符。
 - 将`w`和`h`设得越大，则模型在推理过程中的耗时和内存/显存占用越高。不过，如果`w`和`h`过小，则可能对模型的精度存在较大负面影响。
+- 对于变化检测模型BIT，请保证指定`--fixed_input_shape`，并且数值不包含负数，因为BIT用到空间注意力，需要从tensor中获取`b,c,h,w`的属性，若为负数则报错。
diff --git a/paddlers/custom_models/cd/bit.py b/paddlers/custom_models/cd/bit.py
index 133fd76..af9f2f9 100644
--- a/paddlers/custom_models/cd/bit.py
+++ b/paddlers/custom_models/cd/bit.py
@@ -129,7 +129,7 @@ class BIT(nn.Layer):
             Conv3x3(EBD_DIM, num_classes))
 
     def _get_semantic_tokens(self, x):
-        b, c = paddle.shape(x)[:2]
+        b, c = x.shape[:2]
         att_map = self.conv_att(x)
         att_map = att_map.reshape((b, self.token_len, 1, -1))
         att_map = F.softmax(att_map, axis=-1)
@@ -154,7 +154,7 @@ class BIT(nn.Layer):
         return x
 
     def decode(self, x, m):
-        b, c, h, w = paddle.shape(x)
+        b, c, h, w = x.shape
         x = x.transpose((0, 2, 3, 1)).flatten(1, 2)
         x = self.decoder(x, m)
         x = x.transpose((0, 2, 1)).reshape((b, c, h, w))
@@ -172,7 +172,7 @@ class BIT(nn.Layer):
         else:
             token1 = self._get_reshaped_tokens(x1)
             token2 = self._get_reshaped_tokens(x2)
-
+            
         # Transformer encoder forward
         token = paddle.concat([token1, token2], axis=1)
         token = self.encode(token)
@@ -265,7 +265,7 @@ class CrossAttention(nn.Layer):
             nn.Linear(inner_dim, dim), nn.Dropout(dropout_rate))
 
     def forward(self, x, ref):
-        b, n = paddle.shape(x)[:2]
+        b, n = x.shape[:2]
         h = self.n_heads
 
         q = self.fc_q(x)