Skip to content

M
models

PaddlePaddle / models
10 个月 前同步成功

通知 221
Star 6828
Fork 2962
M
models

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 aa0ab8c9 编写于 作者: W whs 提交者： GitHub
浏览文件
操作

Make ocr and icnet support for python3 (#1178) 

* Make ocr and icnet support for python3

* Restore default arguments.
上级 beb4dfbe
隐藏空白更改
内联 并排
Showing with 89 addition and 65 deletion
fluid/icnet/cityscape.py
浏览文件 @ aa0ab8c9
"""Reader for Cityscape dataset.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import cv2
import numpy as np
......@@ -173,8 +176,8 @@ class DataGenerater:
"""
Scale label according to factor.
"""
h = label.shape[0] / factor
w = label.shape[1] / factor
h = label.shape[0] // factor
w = label.shape[1] // factor
return cv2.resize(
label, (h, w), interpolation=cv2.INTER_NEAREST)[:, :, np.newaxis]
......
fluid/icnet/eval.py
浏览文件 @ aa0ab8c9
......@@ -64,7 +64,7 @@ def eval(args):
exe.run(fluid.default_startup_program())
assert os.path.exists(args.model_path)
fluid.io.load_params(exe, args.model_path)
print "loaded model from: %s" % args.model_path
print("loaded model from: %s" % args.model_path)
sys.stdout.flush()
fetch_vars = [iou, out_w, out_r]
......@@ -80,11 +80,10 @@ def eval(args):
fetch_list=fetch_vars)
out_wrong += result[1]
out_right += result[2]
print "count: %s; current iou: %.3f;\r" % (count, result[0]),
sys.stdout.flush()
iou = cal_mean_iou(out_wrong, out_right)
print "\nmean iou: %.3f" % iou
print "kpis test_acc %f" % iou
print("\nmean iou: %.3f" % iou)
print("kpis test_acc %f" % iou)
def main():
......
fluid/icnet/icnet.py
浏览文件 @ aa0ab8c9
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle.fluid as fluid
import numpy as np
import sys
......@@ -20,8 +23,8 @@ def conv(input,
if padding == "SAME":
padding_h = max(k_h - s_h, 0)
padding_w = max(k_w - s_w, 0)
padding_top = padding_h / 2
padding_left = padding_w / 2
padding_top = padding_h // 2
padding_left = padding_w // 2
padding_bottom = padding_h - padding_top
padding_right = padding_w - padding_left
padding = [
......@@ -57,8 +60,8 @@ def atrous_conv(input,
if padding == "SAME":
padding_h = max(k_h - s_h, 0)
padding_w = max(k_w - s_w, 0)
padding_top = padding_h / 2
padding_left = padding_w / 2
padding_top = padding_h // 2
padding_left = padding_w // 2
padding_bottom = padding_h - padding_top
padding_right = padding_w - padding_left
padding = [
......@@ -141,15 +144,15 @@ def dilation_convs(input):
def pyramis_pooling(input, input_shape):
shape = np.ceil(input_shape / 32).astype("int32")
shape = np.ceil(input_shape // 32).astype("int32")
h, w = shape
pool1 = avg_pool(input, h, w, h, w)
pool1_interp = interp(pool1, shape)
pool2 = avg_pool(input, h / 2, w / 2, h / 2, w / 2)
pool2 = avg_pool(input, h // 2, w // 2, h // 2, w // 2)
pool2_interp = interp(pool2, shape)
pool3 = avg_pool(input, h / 3, w / 3, h / 3, w / 3)
pool3 = avg_pool(input, h // 3, w // 3, h // 3, w // 3)
pool3_interp = interp(pool3, shape)
pool4 = avg_pool(input, h / 4, w / 4, h / 4, w / 4)
pool4 = avg_pool(input, h // 4, w // 4, h // 4, w // 4)
pool4_interp = interp(pool4, shape)
conv5_3_sum = input + pool4_interp + pool3_interp + pool2_interp + pool1_interp
return conv5_3_sum
......@@ -172,14 +175,14 @@ def shared_convs(image):
def res_block(input, filter_num, padding=0, dilation=None, name=None):
tmp = conv(input, 1, 1, filter_num / 4, 1, 1, name=name + "_1_1_reduce")
tmp = conv(input, 1, 1, filter_num // 4, 1, 1, name=name + "_1_1_reduce")
tmp = bn(tmp, relu=True)
tmp = zero_padding(tmp, padding=padding)
if dilation is None:
tmp = conv(tmp, 3, 3, filter_num / 4, 1, 1, name=name + "_3_3")
tmp = conv(tmp, 3, 3, filter_num // 4, 1, 1, name=name + "_3_3")
else:
tmp = atrous_conv(
tmp, 3, 3, filter_num / 4, dilation, name=name + "_3_3")
tmp, 3, 3, filter_num // 4, dilation, name=name + "_3_3")
tmp = bn(tmp, relu=True)
tmp = conv(tmp, 1, 1, filter_num, 1, 1, name=name + "_1_1_increase")
tmp = bn(tmp, relu=False)
......@@ -195,7 +198,7 @@ def proj_block(input, filter_num, padding=0, dilation=None, stride=1,
proj_bn = bn(proj, relu=False)
tmp = conv(
input, 1, 1, filter_num / 4, stride, stride, name=name + "_1_1_reduce")
input, 1, 1, filter_num // 4, stride, stride, name=name + "_1_1_reduce")
tmp = bn(tmp, relu=True)
tmp = zero_padding(tmp, padding=padding)
......@@ -208,7 +211,7 @@ def proj_block(input, filter_num, padding=0, dilation=None, stride=1,
tmp,
3,
3,
filter_num / 4,
filter_num // 4,
1,
1,
padding=padding,
......@@ -218,7 +221,7 @@ def proj_block(input, filter_num, padding=0, dilation=None, stride=1,
tmp,
3,
3,
filter_num / 4,
filter_num // 4,
dilation,
padding=padding,
name=name + "_3_3")
......@@ -232,12 +235,12 @@ def proj_block(input, filter_num, padding=0, dilation=None, stride=1,
def sub_net_4(input, input_shape):
tmp = interp(input, out_shape=np.ceil(input_shape / 32))
tmp = interp(input, out_shape=np.ceil(input_shape // 32))
tmp = dilation_convs(tmp)
tmp = pyramis_pooling(tmp, input_shape)
tmp = conv(tmp, 1, 1, 256, 1, 1, name="conv5_4_k1")
tmp = bn(tmp, relu=True)
tmp = interp(tmp, input_shape / 16)
tmp = interp(tmp, input_shape // 16)
return tmp
......@@ -265,7 +268,7 @@ def CCF24(sub2_out, sub4_out, input_shape):
tmp = bn(tmp, relu=False)
tmp = tmp + sub2_out
tmp = fluid.layers.relu(tmp)
tmp = interp(tmp, input_shape / 8)
tmp = interp(tmp, input_shape // 8)
return tmp
......@@ -275,7 +278,7 @@ def CCF124(sub1_out, sub24_out, input_shape):
tmp = bn(tmp, relu=False)
tmp = tmp + sub1_out
tmp = fluid.layers.relu(tmp)
tmp = interp(tmp, input_shape / 4)
tmp = interp(tmp, input_shape // 4)
return tmp
......
fluid/icnet/infer.py
浏览文件 @ aa0ab8c9
"""Infer for ICNet model."""
from __future__ import print_function
import cityscape
import argparse
import functools
......@@ -101,7 +102,7 @@ def infer(args):
exe.run(fluid.default_startup_program())
assert os.path.exists(args.model_path)
fluid.io.load_params(exe, args.model_path)
print "loaded model from: %s" % args.model_path
print("loaded model from: %s" % args.model_path)
sys.stdout.flush()
if not os.path.isdir(args.out_path):
......
fluid/icnet/train.py
浏览文件 @ aa0ab8c9
"""Trainer for ICNet model."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from icnet import icnet
import cityscape
import argparse
......@@ -94,7 +97,7 @@ def train(args):
exe.run(fluid.default_startup_program())
if args.init_model is not None:
print "load model from: %s" % args.init_model
print("load model from: %s" % args.init_model)
sys.stdout.flush()
fluid.io.load_params(exe, args.init_model)
......@@ -111,7 +114,7 @@ def train(args):
for data in train_reader():
if iter_id > TOTAL_STEP:
end_time = time.time()
print "kpis train_duration %f" % (end_time - start_time)
print("kpis train_duration %f" % (end_time - start_time))
return
iter_id += 1
results = exe.run(
......@@ -123,10 +126,10 @@ def train(args):
sub124_loss += results[3]
# training log
if iter_id % LOG_PERIOD == 0:
print "Iter[%d]; train loss: %.3f; sub4_loss: %.3f; sub24_loss: %.3f; sub124_loss: %.3f" % (
print("Iter[%d]; train loss: %.3f; sub4_loss: %.3f; sub24_loss: %.3f; sub124_loss: %.3f" % (
iter_id, t_loss / LOG_PERIOD, sub4_loss / LOG_PERIOD,
sub24_loss / LOG_PERIOD, sub124_loss / LOG_PERIOD)
print "kpis train_cost %f" % (t_loss / LOG_PERIOD)
sub24_loss / LOG_PERIOD, sub124_loss / LOG_PERIOD))
print("kpis train_cost %f" % (t_loss / LOG_PERIOD))
t_loss = 0.
sub4_loss = 0.
......@@ -137,7 +140,7 @@ def train(args):
if iter_id % CHECKPOINT_PERIOD == 0 and args.checkpoint_path is not None:
dir_name = args.checkpoint_path + "/" + str(iter_id)
fluid.io.save_persistables(exe, dirname=dir_name)
print "Saved checkpoint: %s" % (dir_name)
print("Saved checkpoint: %s" % (dir_name))
def main():
......
fluid/icnet/utils.py
浏览文件 @ aa0ab8c9
......@@ -19,6 +19,7 @@ from __future__ import print_function
import distutils.util
import numpy as np
from paddle.fluid import core
import six
def print_arguments(args):
......@@ -37,7 +38,7 @@ def print_arguments(args):
:type args: argparse.Namespace
"""
print("----------- Configuration Arguments -----------")
for arg, value in sorted(vars(args).iteritems()):
for arg, value in sorted(six.iteritems(vars(args))):
print("%s: %s" % (arg, value))
print("------------------------------------------------")
......
fluid/ocr_recognition/attention_model.py
浏览文件 @ aa0ab8c9
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle.fluid as fluid
decoder_size = 128
......
fluid/ocr_recognition/crnn_ctc_model.py
浏览文件 @ aa0ab8c9
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle.fluid as fluid
from paddle.fluid.layers.learning_rate_scheduler import _decay_step_counter
from paddle.fluid.initializer import init_on_cpu
import math
import six
def conv_bn_pool(input,
......@@ -15,7 +19,7 @@ def conv_bn_pool(input,
pooling=True,
use_cudnn=False):
tmp = input
for i in xrange(group):
for i in six.moves.xrange(group):
tmp = fluid.layers.conv2d(
input=tmp,
num_filters=out_ch[i],
......@@ -192,7 +196,7 @@ def ctc_train_net(args, data_shape, num_classes):
inference_program = fluid.default_main_program().clone(for_test=True)
if learning_rate_decay == "piecewise_decay":
learning_rate = fluid.layers.piecewise_decay([
args.total_step / 4, args.total_step / 2, args.total_step * 3 / 4
args.total_step // 4, args.total_step // 2, args.total_step * 3 // 4
], [LR, LR * 0.1, LR * 0.01, LR * 0.001])
else:
learning_rate = LR
......
fluid/ocr_recognition/data_reader.py
浏览文件 @ aa0ab8c9
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import os
import cv2
import tarfile
......@@ -67,11 +70,11 @@ class DataGenerator(object):
batchsize
) + "; i++) print $(4*i+1)\" \"$(4*i+2)\" \"$(4*i+3)\" \"$(4*i+4);}}' > " + to_file
os.system(cmd)
print "finish batch shuffle"
print("finish batch shuffle")
img_label_lines = open(to_file, 'r').readlines()
def reader():
sizes = len(img_label_lines) / batchsize
sizes = len(img_label_lines) // batchsize
if sizes == 0:
raise ValueError('Batch size is bigger than the dataset size.')
while True:
......
fluid/ocr_recognition/eval.py
浏览文件 @ aa0ab8c9
......@@ -55,17 +55,16 @@ def evaluate(args):
model_dir = os.path.dirname(args.model_path)
model_file_name = os.path.basename(args.model_path)
fluid.io.load_params(exe, dirname=model_dir, filename=model_file_name)
print "Init model from: %s." % args.model_path
print("Init model from: %s." % args.model_path)
evaluator.reset(exe)
count = 0
for data in test_reader():
count += 1
exe.run(fluid.default_main_program(), feed=get_feeder_data(data, place))
print "Read %d samples;\r" % count,
avg_distance, avg_seq_error = evaluator.eval(exe)
print "Read %d samples; avg_distance: %s; avg_seq_error: %s" % (
count, avg_distance, avg_seq_error)
print("Read %d samples; avg_distance: %s; avg_seq_error: %s" % (
count, avg_distance, avg_seq_error))
def main():
......
fluid/ocr_recognition/infer.py
浏览文件 @ aa0ab8c9
from __future__ import print_function
import paddle.v2 as paddle
import paddle.fluid as fluid
from utility import add_arguments, print_arguments, to_lodtensor, get_ctc_feeder_data, get_attention_feeder_for_infer
......@@ -64,7 +65,7 @@ def inference(args):
with open(args.dict) as dict_file:
for i, word in enumerate(dict_file):
dict_map[i] = word.strip()
print "Loaded dict from %s" % args.dict
print("Loaded dict from %s" % args.dict)
# load init model
model_dir = args.model_path
......@@ -73,7 +74,7 @@ def inference(args):
model_dir = os.path.dirname(args.model_path)
model_file_name = os.path.basename(args.model_path)
fluid.io.load_params(exe, dirname=model_dir, filename=model_file_name)
print "Init model from: %s." % args.model_path
print("Init model from: %s." % args.model_path)
batch_times = []
iters = 0
......@@ -96,17 +97,17 @@ def inference(args):
fps = args.batch_size / batch_time
batch_times.append(batch_time)
if dict_map is not None:
print "Iteration %d, latency: %.5f s, fps: %f, result: %s" % (
print("Iteration %d, latency: %.5f s, fps: %f, result: %s" % (
iters,
batch_time,
fps,
[dict_map[index] for index in indexes], )
[dict_map[index] for index in indexes], ))
else:
print "Iteration %d, latency: %.5f s, fps: %f, result: %s" % (
print("Iteration %d, latency: %.5f s, fps: %f, result: %s" % (
iters,
batch_time,
fps,
indexes, )
indexes, ))
iters += 1
......
fluid/ocr_recognition/train.py
浏览文件 @ aa0ab8c9
"""Trainer for OCR CTC or attention model."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import paddle.fluid as fluid
from utility import add_arguments, print_arguments, to_lodtensor, get_ctc_feeder_data, get_attention_feeder_data
import paddle.fluid.profiler as profiler
......@@ -85,7 +88,7 @@ def train(args):
model_dir = os.path.dirname(args.init_model)
model_file_name = os.path.basename(args.init_model)
fluid.io.load_params(exe, dirname=model_dir, filename=model_file_name)
print "Init model from: %s." % args.init_model
print("Init model from: %s." % args.init_model)
train_exe = exe
error_evaluator.reset(exe)
......@@ -112,18 +115,18 @@ def train(args):
for data in test_reader():
exe.run(inference_program, feed=get_feeder_data(data, place))
_, test_seq_error = error_evaluator.eval(exe)
print "\nTime: %s; Iter[%d]; Test seq error: %s.\n" % (
time.time(), iter_num, str(test_seq_error[0]))
print("\nTime: %s; Iter[%d]; Test seq error: %s.\n" % (
time.time(), iter_num, str(test_seq_error[0])))
#Note: The following logs are special for CE monitoring.
#Other situations do not need to care about these logs.
print "kpis test_acc %f" % (1 - test_seq_error[0])
print("kpis test_acc %f" % (1 - test_seq_error[0]))
def save_model(args, exe, iter_num):
filename = "model_%05d" % iter_num
fluid.io.save_params(
exe, dirname=args.save_model_dir, filename=filename)
print "Saved model to: %s/%s." % (args.save_model_dir, filename)
print("Saved model to: %s/%s." % (args.save_model_dir, filename))
iter_num = 0
stop = False
......@@ -152,14 +155,14 @@ def train(args):
iter_num += 1
# training log
if iter_num % args.log_period == 0:
print "\nTime: %s; Iter[%d]; Avg loss: %.3f; Avg seq err: %.3f" % (
print("\nTime: %s; Iter[%d]; Avg loss: %.3f; Avg seq err: %.3f" % (
time.time(), iter_num,
total_loss / (args.log_period * args.batch_size),
total_seq_error / (args.log_period * args.batch_size))
print "kpis train_cost %f" % (total_loss / (args.log_period *
args.batch_size))
print "kpis train_acc %f" % (
1 - total_seq_error / (args.log_period * args.batch_size))
total_seq_error / (args.log_period * args.batch_size)))
print("kpis train_cost %f" % (total_loss / (args.log_period *
args.batch_size)))
print("kpis train_acc %f" % (
1 - total_seq_error / (args.log_period * args.batch_size)))
total_loss = 0.0
total_seq_error = 0.0
......@@ -179,7 +182,7 @@ def train(args):
else:
save_model(args, exe, iter_num)
end_time = time.time()
print "kpis train_duration %f" % (end_time - start_time)
print("kpis train_duration %f" % (end_time - start_time))
# Postprocess benchmark data
latencies = batch_times[args.skip_batch_num:]
latency_avg = np.average(latencies)
......
fluid/ocr_recognition/utility.py
浏览文件 @ aa0ab8c9
......@@ -20,6 +20,7 @@ import distutils.util
import numpy as np
from paddle.fluid import core
import paddle.fluid as fluid
import six
def print_arguments(args):
......@@ -38,7 +39,7 @@ def print_arguments(args):
:type args: argparse.Namespace
"""
print("----------- Configuration Arguments -----------")
for arg, value in sorted(vars(args).iteritems()):
for arg, value in sorted(six.iteritems(vars(args))):
print("%s: %s" % (arg, value))
print("------------------------------------------------")
......@@ -82,9 +83,9 @@ def get_ctc_feeder_data(data, place, need_label=True):
pixel_tensor = core.LoDTensor()
pixel_data = None
pixel_data = np.concatenate(
map(lambda x: x[0][np.newaxis, :], data), axis=0).astype("float32")
list(map(lambda x: x[0][np.newaxis, :], data)), axis=0).astype("float32")
pixel_tensor.set(pixel_data, place)
label_tensor = to_lodtensor(map(lambda x: x[1], data), place)
label_tensor = to_lodtensor(list(map(lambda x: x[1], data)), place)
if need_label:
return {"pixel": pixel_tensor, "label": label_tensor}
else:
......@@ -95,10 +96,10 @@ def get_attention_feeder_data(data, place, need_label=True):
pixel_tensor = core.LoDTensor()
pixel_data = None
pixel_data = np.concatenate(
map(lambda x: x[0][np.newaxis, :], data), axis=0).astype("float32")
list(map(lambda x: x[0][np.newaxis, :], data)), axis=0).astype("float32")
pixel_tensor.set(pixel_data, place)
label_in_tensor = to_lodtensor(map(lambda x: x[1], data), place)
label_out_tensor = to_lodtensor(map(lambda x: x[2], data), place)
label_in_tensor = to_lodtensor(list(map(lambda x: x[1], data)), place)
label_out_tensor = to_lodtensor(list(map(lambda x: x[2], data)), place)
if need_label:
return {
"pixel": pixel_tensor,
......@@ -126,7 +127,7 @@ def get_attention_feeder_for_infer(data, place):
pixel_tensor = core.LoDTensor()
pixel_data = None
pixel_data = np.concatenate(
map(lambda x: x[0][np.newaxis, :], data), axis=0).astype("float32")
list(map(lambda x: x[0][np.newaxis, :], data)), axis=0).astype("float32")
pixel_tensor.set(pixel_data, place)
return {
"pixel": pixel_tensor,
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或