opensource/PaddleOCR
3
0
Fork 0
mirror of https://github.com/PaddlePaddle/PaddleOCR.git synced 2026-09-24 23:33:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

modified config and resnet31

Browse Source
This commit is contained in:
smilelite
2022-07-14 23:11:20 +08:00
parent e181622756
commit 7c5b47069e
2 changed files with 33 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/rec/rec_r31_robustscanner.yml
+3 -3
View File
@@ -39,6 +39,7 @@ Architecture:
Transform:
Backbone:
name: ResNet31
init_type: KaimingNormal
Head:
name: RobustScannerHead
enc_outchannles: 128
@@ -64,9 +65,8 @@ Metric:
Train:
dataset:
name: SimpleDataSet
label_file_list: ['./train_data/train_list.txt']
data_dir: ./train_data/
name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/training/
transforms:
- DecodeImage: # load image
img_mode: BGR
ppocr/modeling/backbones/rec_resnet_31.py
+30 -15
View File
@@ -29,11 +29,7 @@ import numpy as np
__all__ = ["ResNet31"]
conv_weight_attr = nn.initializer.KaimingNormal()
bn_weight_attr = ParamAttr(initializer=nn.initializer.Uniform(), learning_rate=1)
def conv3x3(in_channel, out_channel, stride=1):
def conv3x3(in_channel, out_channel, stride=1, conv_weight_attr=None):
return nn.Conv2D(
in_channel,
out_channel,
@@ -47,12 +43,14 @@ def conv3x3(in_channel, out_channel, stride=1):
class BasicBlock(nn.Layer):
expansion = 1
def __init__(self, in_channels, channels, stride=1, downsample=False):
def __init__(self, in_channels, channels, stride=1, downsample=False, conv_weight_attr=None, bn_weight_attr=None):
super().__init__()
self.conv1 = conv3x3(in_channels, channels, stride)
self.conv1 = conv3x3(in_channels, channels, stride,
conv_weight_attr=conv_weight_attr)
self.bn1 = nn.BatchNorm2D(channels, weight_attr=bn_weight_attr)
self.relu = nn.ReLU()
self.conv2 = conv3x3(channels, channels)
self.conv2 = conv3x3(channels, channels,
conv_weight_attr=conv_weight_attr)
self.bn2 = nn.BatchNorm2D(channels, weight_attr=bn_weight_attr)
self.downsample = downsample
if downsample:
@@ -96,6 +94,7 @@ class ResNet31(nn.Layer):
channels (list[int]): List of out_channels of Conv2d layer.
out_indices (None | Sequence[int]): Indices of output stages.
last_stage_pool (bool): If True, add `MaxPool2d` layer to last stage.
init_type (None | str): the config to control the initialization.
'''
def __init__(self,
@@ -103,7 +102,8 @@ class ResNet31(nn.Layer):
layers=[1, 2, 5, 3],
channels=[64, 128, 256, 256, 512, 512, 512],
out_indices=None,
last_stage_pool=False):
last_stage_pool=False,
init_type=None):
super(ResNet31, self).__init__()
assert isinstance(in_channels, int)
assert isinstance(last_stage_pool, bool)
@@ -111,6 +111,16 @@ class ResNet31(nn.Layer):
self.out_indices = out_indices
self.last_stage_pool = last_stage_pool
conv_weight_attr = None
bn_weight_attr = None
if init_type is not None:
support_dict = ['KaimingNormal']
assert init_type in support_dict, Exception(
"resnet31 only support {}".format(support_dict))
conv_weight_attr = nn.initializer.KaimingNormal()
bn_weight_attr = ParamAttr(initializer=nn.initializer.Uniform(), learning_rate=1)
# conv 1 (Conv Conv)
self.conv1_1 = nn.Conv2D(
in_channels, channels[0], kernel_size=3, stride=1, padding=1, weight_attr=conv_weight_attr)
@@ -125,7 +135,8 @@ class ResNet31(nn.Layer):
# conv 2 (Max-pooling, Residual block, Conv)
self.pool2 = nn.MaxPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True)
self.block2 = self._make_layer(channels[1], channels[2], layers[0])
self.block2 = self._make_layer(channels[1], channels[2], layers[0],
conv_weight_attr=conv_weight_attr, bn_weight_attr=bn_weight_attr)
self.conv2 = nn.Conv2D(
channels[2], channels[2], kernel_size=3, stride=1, padding=1, weight_attr=conv_weight_attr)
self.bn2 = nn.BatchNorm2D(channels[2], weight_attr=bn_weight_attr)
@@ -134,7 +145,8 @@ class ResNet31(nn.Layer):
# conv 3 (Max-pooling, Residual block, Conv)
self.pool3 = nn.MaxPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True)
self.block3 = self._make_layer(channels[2], channels[3], layers[1])
self.block3 = self._make_layer(channels[2], channels[3], layers[1],
conv_weight_attr=conv_weight_attr, bn_weight_attr=bn_weight_attr)
self.conv3 = nn.Conv2D(
channels[3], channels[3], kernel_size=3, stride=1, padding=1, weight_attr=conv_weight_attr)
self.bn3 = nn.BatchNorm2D(channels[3], weight_attr=bn_weight_attr)
@@ -143,7 +155,8 @@ class ResNet31(nn.Layer):
# conv 4 (Max-pooling, Residual block, Conv)
self.pool4 = nn.MaxPool2D(
kernel_size=(2, 1), stride=(2, 1), padding=0, ceil_mode=True)
self.block4 = self._make_layer(channels[3], channels[4], layers[2])
self.block4 = self._make_layer(channels[3], channels[4], layers[2],
conv_weight_attr=conv_weight_attr, bn_weight_attr=bn_weight_attr)
self.conv4 = nn.Conv2D(
channels[4], channels[4], kernel_size=3, stride=1, padding=1, weight_attr=conv_weight_attr)
self.bn4 = nn.BatchNorm2D(channels[4], weight_attr=bn_weight_attr)
@@ -154,7 +167,8 @@ class ResNet31(nn.Layer):
if self.last_stage_pool:
self.pool5 = nn.MaxPool2D(
kernel_size=2, stride=2, padding=0, ceil_mode=True)
self.block5 = self._make_layer(channels[4], channels[5], layers[3])
self.block5 = self._make_layer(channels[4], channels[5], layers[3],
conv_weight_attr=conv_weight_attr, bn_weight_attr=bn_weight_attr)
self.conv5 = nn.Conv2D(
channels[5], channels[5], kernel_size=3, stride=1, padding=1, weight_attr=conv_weight_attr)
self.bn5 = nn.BatchNorm2D(channels[5], weight_attr=bn_weight_attr)
@@ -162,7 +176,7 @@ class ResNet31(nn.Layer):
self.out_channels = channels[-1]
def _make_layer(self, input_channels, output_channels, blocks):
def _make_layer(self, input_channels, output_channels, blocks, conv_weight_attr=None, bn_weight_attr=None):
layers = []
for _ in range(blocks):
downsample = None
@@ -179,7 +193,8 @@ class ResNet31(nn.Layer):
layers.append(
BasicBlock(
input_channels, output_channels, downsample=downsample))
input_channels, output_channels, downsample=downsample,
conv_weight_attr=conv_weight_attr, bn_weight_attr=bn_weight_attr))
input_channels = output_channels
return nn.Sequential(*layers)