#!/usr/bin/python
# -*- coding: UTF-8 -*-
from __future__ import print_function
caffe_root = '/home/jhy/caffe-ssd/'
import os
os.chdir(caffe_root)
import sys
sys.path.insert(0, '/home/jhy/caffe-ssd/python')
import caffe
from caffe.model_libs import *
from google.protobuf import text_format
import math
import os
import shutil
import stat
import subprocess
import sys
def AddExtraLayers(net, use_batchnorm=True, lr_mult=1):
use_relu = True
# Add additional convolutional layers.
# 19 x 19
from_layer = net.keys()[-1]
# TODO(weiliu89): Construct the name using the last layer to avoid duplication.
# 10 x 10
out_layer = "conv6_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv6_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 512, 3, 1, 2,
lr_mult=lr_mult)
# 5 x 5
from_layer = out_layer
out_layer = "conv7_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv7_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 1, 2,
lr_mult=lr_mult)
# 3 x 3
from_layer = out_layer
out_layer = "conv8_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv8_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1,
lr_mult=lr_mult)
# 1 x 1
from_layer = out_layer
out_layer = "conv9_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv9_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1,
lr_mult=lr_mult)
return net
### Modify the following parameters accordingly ###
# The directory which contains the caffe code.
# We assume you are running the script at the CAFFE_ROOT.
caffe_root = os.getcwd()
# Set true if you want to start training right after generating all files.
run_soon = True
# Set true if you want to load from most recently saved snapshot.
# Otherwise, we will load from the pretrain_model defined below.
resume_training = True
# If true, Remove old model files.
remove_old_models = False
# The database file for training data. Created by data/VOC0712/create_data.sh
train_data = "examples/dronedata/dronedata_trainval_lmdb"
# The database file for testing data. Created by data/VOC0712/create_data.sh
test_data = "examples/dronedata/dronedata_test_lmdb"
# Specify the batch sampler.
resize_width = 512
resize_height = 512
resize = "{}x{}".format(resize_width, resize_height) #resie = 512×512
batch_sampler = [
{
'sampler': {
},
'max_trials': 1,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.1,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.3,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.5,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.7,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.9,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'max_jaccard_overlap': 1.0,
},
'max_trials': 50,
'max_sample': 1,
},
]
train_transform_param = {
'mirror': True,
'mean_value': [104, 117, 123],
'force_color':True,
'resize_param': {
'prob': 1,
'resize_mode': P.Resize.WARP,
'height': resize_height,
'width': resize_width,
'interp_mode': [
P.Resize.LINEAR,
P.Resize.AREA,
P.Resize.NEAREST,
P.Resize.CUBIC,
P.Resize.LANCZOS4,
],
},
'distort_param': {
'brightness_prob': 0.5,
'brightness_delta': 32,
'contrast_prob': 0.5,
'contrast_lower': 0.5,
'contrast_upper': 1.5,
'hue_prob': 0.5,
'hue_delta': 18,
'saturation_prob': 0.5,
'saturation_lower': 0.5,
'saturation_upper': 1.5,
'random_order_prob': 0.0,
},
'expand_param': {
'prob': 0.5,
'max_expand_ratio': 4.0,
},
'emit_constraint': {
'emit_type': caffe_pb2.EmitConstraint.CENTER,
}
}
test_transform_param = {
'mean_value': [104, 117, 123],
'force_color':True,
'resize_param': {
'prob': 1,
'resize_mode': P.Resize.WARP,
'height': resize_height,
'width': resize_width,
'interp_mode': [P.Resize.LINEAR],
},
}
# If true, use batch norm for all newly added layers.
# Currently only the non batch norm version has been tested.
use_batchnorm = False
lr_mult = 1
# Use different initial learning rate.
if use_batchnorm:
base_lr = 0.0004
else:
# A learning rate for batch_size = 1, num_gpus = 1.
base_lr = 0.000008
# Modify the job name if you want.
job_name = "SSD_{}".format(resize)#SSD_512x512
# The name of the model. Modify it if you want.
model_name = "VGG_jhyDrone_{}".format(job_name)
# Directory which stores the model .prototxt file.
save_dir = "/home/jhy/models/VGGNet/jhyDrone/{}".format(job_name)
# Directory which stores the snapshot of models.�
snapshot_dir = "/home/jhy/models/VGGNet/jhyDrone/{}".format(job_name)
# Directory which stores the job script and log file.
job_dir = "/home/jhy/jobs/VGGNet/jhyDrone/{}".format(job_name)
# Directory which stores the detection results.
output_result_dir = "{}/data/VOCdevkit/results/jhyDrone/{}/Main".format(os.environ['HOME'], job_name)
#output_result_dir = "{}/data/VOCdevkit/results/jhyDrone/{}/Main".format(os.environ['LVMDATA'], job_name)
# model definition files.模型定义文件
train_net_file = "{}/train.prototxt".format(save_dir)
test_net_file = "{}/test.prototxt".format(save_dir)
deploy_net_file = "{}/deploy.prototxt".format(save_dir)
solver_file = "{}/solver.prototxt".format(save_dir)
# snapshot prefix.快照前缀
snapshot_prefix = "{}/{}".format(snapshot_dir, model_name)
# job script path.
job_file = "{}/{}.sh".format(job_dir, model_name)
# Stores the test image names and sizes. Created by data/VOC0712/create_list.sh
#存储测试图片的名称和大小。由数据/ VOC0712 / create_list.sh
name_size_file = "data/dronedata/test_name_size.txt"
# The pretrained model. We use the Fully convolutional reduced (atrous) VGGNet.
pretrain_model = "/home/jhy/models/VGGNet/VGG_ILSVRC_16_layers_fc_reduced.caffemodel"
# Stores LabelMapItem.
label_map_file = "data/dronedata/labelmap_voc.prototxt"
# MultiBoxLoss parameters.
num_classes = 2
share_location = True
background_label_id=0
train_on_diff_gt = True
normalization_mode = P.Loss.VALID
code_type = P.PriorBox.CENTER_SIZE
ignore_cross_boundary_bbox = False
mining_type = P.MultiBoxLoss.MAX_NEGATIVE
neg_pos_ratio = 2
loc_weight = (neg_pos_ratio + 1.) / 4.
multibox_loss_param = {
'loc_loss_type': P.MultiBoxLoss.SMOOTH_L1,
'conf_loss_type': P.MultiBoxLoss.SOFTMAX,
'loc_weight': loc_weight,
'num_classes': num_classes,
'share_location': share_location,
'match_type': P.MultiBoxLoss.PER_PREDICTION,
'overlap_threshold': 0.5,
'use_prior_for_matching': True,
'background_label_id': background_label_id,
'use_difficult_gt': train_on_diff_gt,
'mining_type': mining_type,
'neg_pos_ratio': neg_pos_ratio,
'neg_overlap': 0.5,
'code_type': code_type,
'ignore_cross_boundary_bbox': ignore_cross_boundary_bbox,
}
loss_param = {
'normalization': normalization_mode,
}
# parameters for generating priors.
# minimum dimension of input image
min_dim = 512
# conv4_3 ==> 38 x 38
# fc7 ==> 19 x 19
# conv6_2 ==> 10 x 10
# conv7_2 ==> 5 x 5
# conv8_2 ==> 3 x 3
# conv9_2 ==> 1 x 1
mbox_source_layers = ['conv4_3', 'fc7', 'conv6_2', 'conv7_2', 'conv8_2', 'conv9_2']
# in percent %
min_ratio = 20
max_ratio = 90
step = int(math.floor((max_ratio - min_ratio) / (len(mbox_source_layers) - 2)))
min_sizes = []
max_sizes = []
for ratio in range(min_ratio, max_ratio + 1, step):
min_sizes.append(min_dim * ratio / 100.)
max_sizes.append(min_dim * (ratio + step) / 100.)
min_sizes = [min_dim * 10 / 100.] + min_sizes
max_sizes = [min_dim * 20 / 100.] + max_sizes
steps = [8, 16, 32, 64, 100, 300]
aspect_ratios = [[2], [2, 3], [2, 3], [2, 3], [2], [2]]
# L2 normalize conv4_3.
normalizations = [20, -1, -1, -1, -1, -1]
# variance used to encode/decode prior bboxes.
if code_type == P.PriorBox.CENTER_SIZE:
prior_variance = [0.1, 0.1, 0.2, 0.2]
else:
prior_variance = [0.1]
flip = True
clip = False
# Solver parameters.
# Defining which GPUs to use.
gpus = "0,1,2"
#gpus = "0"
gpulist = gpus.split(",")
num_gpus = len(gpulist)
# Divide the mini-batch to different GPUs.
batch_size = 32
accum_batch_size = 32
iter_size = accum_batch_size / batch_size
solver_mode = P.Solver.CPU
device_id = 0
batch_size_per_device = batch_size
if num_gpus > 0:
batch_size_per_device = int(math.ceil(float(batch_size) / num_gpus))
iter_size = int(math.ceil(float(accum_batch_size) / (batch_size_per_device * num_gpus)))
solver_mode = P.Solver.GPU
device_id = int(gpulist[0])
if normalization_mode == P.Loss.NONE:
base_lr /= batch_size_per_device
elif normalization_mode == P.Loss.VALID:
base_lr *= 25. / loc_weight
elif normalization_mode == P.Loss.FULL:
# Roughly there are 2000 prior bboxes per image.
# TODO(weiliu89): Estimate the exact # of priors.
base_lr *= 2000.
# Evaluate on whole test set.
#num_test_image = 86
num_test_image = 10
test_batch_size = 1
# Ideally test_batch_size should be divisible by num_test_image,
# otherwise mAP will be slightly off the true value.
test_iter = int(math.ceil(float(num_test_image) / test_batch_size))
solver_param = {
# Train parameters
'base_lr': base_lr,
'weight_decay': 0.0005,
'lr_policy': "multistep",
'stepvalue': [8000, 10000, 12000],
'gamma': 0.1,
'momentum': 0.9,
'iter_size': iter_size,
'max_iter': 120000,
'snapshot': 10000,
'display': 10,
'average_loss': 10,
'type': "SGD",
'solver_mode': solver_mode,
'device_id': device_id,
'debug_info': False,
'snapshot_after_train': True,
# Test parameters
'test_iter': [test_iter],
'test_interval': 500,
'eval_type': "detection",
'ap_version': "11point",
'test_initialization': False,
'show_per_class_result': True,
}
# parameters for generating detection output.
det_out_param = {
'num_classes': num_classes,
'share_location': share_location,
'background_label_id': background_label_id,
'nms_param': {'nms_threshold': 0.45, 'top_k': 400},
'save_output_param': {
'output_directory': output_result_dir,
'output_name_prefix': "comp4_det_test_",
'output_format': "VOC",
'label_map_file': label_map_file,
'name_size_file': name_size_file,
'num_test_image': num_test_image,
},
'keep_top_k': 200,
'confidence_threshold': 0.01,
'code_type': code_type,
}
# parameters for evaluating detection results.
det_eval_param = {
'num_classes': num_classes,
'background_label_id': background_label_id,
'overlap_threshold': 0.5,
'evaluate_difficult_gt': False,
'name_size_file': name_size_file,
}
### Hopefully you don't need to change the following ###
# Check file.
check_if_exist(train_data)
check_if_exist(test_data)
check_if_exist(label_map_file)
check_if_exist(pretrain_model)
make_if_not_exist(save_dir)
make_if_not_exist(job_dir)
make_if_not_exist(snapshot_dir)
# Create train net.
net = caffe.NetSpec()
net.data, net.label = CreateAnnotatedDataLayer(train_data, batch_size=batch_size_per_device,
train=True, output_label=True, label_map_file=label_map_file,
transform_param=train_transform_param, batch_sampler=batch_sampler)
VGGNetBody(net, from_layer='data', fully_conv=True, reduced=True, dilated=True,
dropout=False)
AddExtraLayers(net, use_batchnorm, lr_mult=lr_mult)
mbox_layers = CreateMultiBoxHead(net, data_layer='data', from_layers=mbox_source_layers,
use_batchnorm=use_batchnorm, min_sizes=min_sizes, max_sizes=max_sizes,
aspect_ratios=aspect_ratios, steps=steps, normalizations=normalizations,
num_classes=num_classes, share_location=share_location, flip=flip, clip=clip,
prior_variance=prior_variance, kernel_size=3, pad=1, lr_mult=lr_mult)
# Create the MultiBoxLossLayer.
name = "mbox_loss"
mbox_layers.append(net.label)
net[name] = L.MultiBoxLoss(*mbox_layers, multibox_loss_param=multibox_loss_param,
loss_param=loss_param, include=dict(phase=caffe_pb2.Phase.Value('TRAIN')),
propagate_down=[True, True, False, False])
with open(train_net_file, 'w') as f:
print('name: "{}_train"'.format(model_name), file=f)
print(net.to_proto(), file=f)
shutil.copy(train_net_file, job_dir)
# Create test net.
net = caffe.NetSpec()
net.data, net.label = CreateAnnotatedDataLayer(test_data, batch_size=test_batch_size,
train=False, output_label=True, label_map_file=label_map_file,
transform_param=test_transform_param)
VGGNetBody(net, from_layer='data', fully_conv=True, reduced=True, dilated=True,
dropout=False)
AddExtraLayers(net, use_batchnorm, lr_mult=lr_mult)
mbox_layers = CreateMultiBoxHead(net, data_layer='data', from_layers=mbox_source_layers,
use_batchnorm=use_batchnorm, min_sizes=min_sizes, max_sizes=max_sizes,
aspect_ratios=aspect_ratios, steps=steps, normalizations=normalizations,
num_classes=num_classes, share_location=share_location, flip=flip, clip=clip,
prior_variance=prior_variance, kernel_size=3, pad=1, lr_mult=lr_mult)
conf_name = "mbox_conf"
if multibox_loss_param["conf_loss_type"] == P.MultiBoxLoss.SOFTMAX:
reshape_name = "{}_reshape".format(conf_name)
net[reshape_name] = L.Reshape(net[conf_name], shape=dict(dim=[0, -1, num_classes]))
softmax_name = "{}_softmax".format(conf_name)
net[softmax_name] = L.Softmax(net[reshape_name], axis=2)
flatten_name = "{}_flatten".format(conf_name)
net[flatten_name] = L.Flatten(net[softmax_name], axis=1)
mbox_layers[1] = net[flatten_name]
elif multibox_loss_param["conf_loss_type"] == P.MultiBoxLoss.LOGISTIC:
sigmoid_name = "{}_sigmoid".format(conf_name)
net[sigmoid_name] = L.Sigmoid(net[conf_name])
mbox_layers[1] = net[sigmoid_name]
net.detection_out = L.DetectionOutput(*mbox_layers,
detection_output_param=det_out_param,
include=dict(phase=caffe_pb2.Phase.Value('TEST')))
net.detection_eval = L.DetectionEvaluate(net.detection_out, net.label,
detection_evaluate_param=det_eval_param,
include=dict(phase=caffe_pb2.Phase.Value('TEST')))
with open(test_net_file, 'w') as f:
print('name: "{}_test"'.format(model_name), file=f)
print(net.to_proto(), file=f)
shutil.copy(test_net_file, job_dir)
# Create deploy net.
# Remove the first and last layer from test net.
deploy_net = net
with open(deploy_net_file, 'w') as f:
net_param = deploy_net.to_proto()
# Remove the first (AnnotatedData) and last (DetectionEvaluate) layer from test net.
del net_param.layer[0]
del net_param.layer[-1]
net_param.name = '{}_deploy'.format(model_name)
net_param.input.extend(['data'])
net_param.input_shape.extend([
caffe_pb2.BlobShape(dim=[1, 3, resize_height, resize_width])])
print(net_param, file=f)
shutil.copy(deploy_net_file, job_dir)
# Create solver.
solver = caffe_pb2.SolverParameter(
train_net=train_net_file,
test_net=[test_net_file],
snapshot_prefix=snapshot_prefix,
**solver_param)
with open(solver_file, 'w') as f:
print(solver, file=f)
shutil.copy(solver_file, job_dir)
max_iter = 0
# Find most recent snapshot.
for file in os.listdir(snapshot_dir):
if file.endswith(".solverstate"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if iter > max_iter:
max_iter = iter
train_src_param = '--weights="{}" \\\n'.format(pretrain_model)
if resume_training:
if max_iter > 0:
train_src_param = '--snapshot="{}_iter_{}.solverstate" \\\n'.format(snapshot_prefix, max_iter)
if remove_old_models:
# Remove any snapshots smaller than max_iter.
for file in os.listdir(snapshot_dir):
if file.endswith(".solverstate"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if max_iter > iter:
os.remove("{}/{}".format(snapshot_dir, file))
if file.endswith(".caffemodel"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if max_iter > iter:
os.remove("{}/{}".format(snapshot_dir, file))
# Create job file.
with open(job_file, 'w') as f:
f.write('cd {}\n'.format(caffe_root))
f.write('./build/tools/caffe train \\\n')
f.write('--solver="{}" \\\n'.format(solver_file))
f.write(train_src_param)
if solver_param['solver_mode'] == P.Solver.GPU:
f.write('--gpu {} 2>&1 | tee {}/{}.log\n'.format(gpus, job_dir, model_name))
else:
f.write('2>&1 | tee {}/{}.log\n'.format(job_dir, model_name))
# Copy the python script to job_dir.
print("1111111111111")
#py_file = os.path.abspath(__file__)
py_file = "/home/jhy/caffe-ssd/ssd_pascal_jhyDrone.py"
print(py_file)
shutil.copy(py_file, job_dir)
# Run the job.
os.chmod(job_file, stat.S_IRWXU)# 对于拥有者读写执行的权限
if run_soon:
subprocess.call(job_file, shell=True)
from __future__ import print_function
import numpy as np
import matplotlib.pyplot as plt
import pylab
import datetime
from PIL import Image
import os
# the path of caffe & the path of python in caffe
import sys,getopt
sys.path.append('/home/jhy/caffe-ssd/python')
import caffe
caffe_root = '/home/jhy/caffe-ssd/'
#caffe.set_mode_cpu()
caffe.set_mode_gpu()
caffe.set_device(0)
from google.protobuf import text_format
from caffe.proto import caffe_pb2
plt.rcParams['figure.figsize'] = (10, 10)
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
model_def = '/home/jhy/wave_test/deploy.prototxt'
model_weights = '/home/jhy/wave_test/VGG_jhyDrone_SSD_512x512_iter_100000.caffemodel'
#labelmap_file = '/home/jhy/wave_test/labelmap_voc.prototxt'
labelmap_file = '/home/jhy/caffe-ssd/data/dronedata/labelmap_voc.prototxt'
#get parameter
def GetJPGName(InputImagePath):
jpg_names = []
jpgs = os.listdir(InputImagePath)
for one_jpg in jpgs:
if os.path.splitext(one_jpg)[1] == '.jpg':
jpg_names.append(one_jpg)
return jpg_names
def WrongInput():
print("Usage: python brdge_test.py -i InputImagePath -o OutputImagePath -s score -l OutputCSVFileName")
sys.exit(1)
def GetPara():
try:
opts, args = getopt.getopt(sys.argv[1:], "i:o:s:l:")
except getopt.GetoptError:
WrongInput()
#get options into dictionary
option=[]
value=[]
for opt,val in opts:
option.append(opt)
value.append(val)
parameter = dict(zip(option,value))
#check para
if len(parameter.keys()) != 4:
WrongInput()
return parameter['-i'],parameter['-o'], parameter['-s'], parameter['-l']
#about result.csv
def InitCSV(OutputCSVFileName):
WriteCSVFile = open(OutputCSVFileName, 'w')
WriteCSVFile.write( ",".join(['0','1','2','3','4','5','6']) + "\n" )
WriteCSVFile.write( ",".join(['image_name','x1','y1','x2','y2','label','score']) + "\n" )
WriteCSVFile.close()
def WriteinCSV(OutputCSVFileName,image_name,xmin,ymin,xmax,ymax,label_name,score):
WriteCSVFile = open(OutputCSVFileName, 'a')
one_line_data = [image_name,xmin,ymin,xmax,ymax,label_name,score]
WriteCSVFile.write( ",".join(one_line_data) + "\n" )
WriteCSVFile.close()
def RunDetection(InputImagePath, OutputImagePath, jpg_names, score_threshold):
net = caffe.Net(model_def, model_weights, caffe.TEST)
for one_jpg in jpg_names:
load_path = os.path.join( InputImagePath + '/' + one_jpg )
save_path = os.path.join( OutputImagePath + '/' + one_jpg )
image = caffe.io.load_image(load_path)
# net = caffe.Net(model_def, model_weights, caffe.TEST)
transformer = caffe.io.Transformer({'data': net.blobs['data'].data.shape})
transformer.set_transpose('data', (2, 0, 1))
transformer.set_mean('data', np.array([104, 117, 123])) # mean pixel
transformer.set_raw_scale('data', 255) # the reference model operates on images in [0,255] range instead of [0,1]
transformer.set_channel_swap('data',(2, 1, 0)) # the reference model has channels in BGR order instead of RGB
image_resize = 512
net.blobs['data'].reshape(1, 3, image_resize, image_resize)
transformed_image = transformer.preprocess('data', image)
# transformed_image = detection_init(labelmap_file, net, image)
net.blobs['data'].data[...] = transformed_image
detections = net.forward()['detection_out']
# Parse the outputs.
det_label = detections[0, 0, :, 1]
det_conf = detections[0, 0, :, 2]
det_xmin = detections[0, 0, :, 3]
det_ymin = detections[0, 0, :, 4]
det_xmax = detections[0, 0, :, 5]
det_ymax = detections[0, 0, :, 6]
# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= score_threshold]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
# get_lablename_fcn
file = open(labelmap_file, 'r')
labelmap = caffe_pb2.LabelMap()
text_format.Merge(str(file.read()), labelmap)
num_labels = len(labelmap.item)
labelnames = []
for label in top_label_indices:
found = False
for i in range(0, num_labels):
if label == labelmap.item[i].label:
found = True
labelnames.append(labelmap.item[i].display_name)
break
assert found == True
top_labels = labelnames
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]
# Plot the boxes in test picture
colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
plt.switch_backend('agg')
currentAxis = plt.gca()
if top_conf.shape[0] == 0:
print(one_jpg)
for i in range(top_conf.shape[0]):
# bbox value
xmin = int(round(top_xmin[i] * image.shape[1]))
ymin = int(round(top_ymin[i] * image.shape[0]))
xmax = int(round(top_xmax[i] * image.shape[1]))
ymax = int(round(top_ymax[i] * image.shape[0]))
# score
score = top_conf[i]
# label
label = int(top_label_indices[i])
label_name = top_labels[i]
# display info2: label score xmin ymin xmax ymax
#display_txt = ''
display_txt = '%s: %.2f' % (label_name, score)
#write in CSV
WriteinCSV("/home/jhy/wave_test/reult_forktest_images/result.csv", "forktest_images/"+one_jpg, str(xmin), str(ymin), str(xmax), str(ymax) ,label_name, str(score) )
# display info1: label score
coords = (xmin, ymin), xmax - xmin + 1, ymax - ymin + 1
color = colors[label]
currentAxis.add_patch( plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2) )
currentAxis.text( xmin, ymin, display_txt, bbox={'facecolor': color,'alpha': 0.5} )
plt.imshow(image)
plt.axis('off')
plt.savefig(save_path,bbox_inches='tight')
label_set = set(top_labels)
if __name__ == '__main__':
InputImagePath,OutputImagePath,score_threshold,OutputCSVFileName = GetPara()
InitCSV(OutputCSVFileName)
jpg_names = GetJPGName(InputImagePath)
RunDetection(InputImagePath, OutputImagePath, jpg_names, float(score_threshold) )
#encoding=utf8
'''
Detection with SSD
In this example, we will load a SSD model and use it to detect objects.
'''
import os
import sys
import argparse
import numpy as np
from PIL import Image, ImageDraw
# Make sure that caffe is on the python path:
caffe_root = './'
os.chdir(caffe_root)
sys.path.insert(0, os.path.join(caffe_root, 'python'))
import caffe
from google.protobuf import text_format
from caffe.proto import caffe_pb2
def get_labelname(labelmap, labels):
num_labels = len(labelmap.item)
labelnames = []
if type(labels) is not list:
labels = [labels]
for label in labels:
found = False
for i in xrange(0, num_labels):
if label == labelmap.item[i].label:
found = True
labelnames.append(labelmap.item[i].display_name)
break
assert found == True
return labelnames
class CaffeDetection:
def __init__(self, gpu_id, model_def, model_weights, image_resize, labelmap_file):
caffe.set_device(gpu_id)
caffe.set_mode_gpu()
self.image_resize = image_resize
# Load the net in the test phase for inference, and configure input preprocessing.
self.net = caffe.Net(model_def, # defines the structure of the model
model_weights, # contains the trained weights
caffe.TEST) # use test mode (e.g., don't perform dropout)
# input preprocessing: 'data' is the name of the input blob == net.inputs[0]
self.transformer = caffe.io.Transformer({'data': self.net.blobs['data'].data.shape})
self.transformer.set_transpose('data', (2, 0, 1))
self.transformer.set_mean('data', np.array([104, 117, 123])) # mean pixel
# the reference model operates on images in [0,255] range instead of [0,1]
self.transformer.set_raw_scale('data', 255)
# the reference model has channels in BGR order instead of RGB
self.transformer.set_channel_swap('data', (2, 1, 0))
# load PASCAL VOC labels
file = open(labelmap_file, 'r')
self.labelmap = caffe_pb2.LabelMap()
text_format.Merge(str(file.read()), self.labelmap)
def detect(self, image_file, conf_thresh=0.5, topn=5):
'''
SSD detection
'''
# set net to batch size of 1
# image_resize = 300
self.net.blobs['data'].reshape(1, 3, self.image_resize, self.image_resize)
image = caffe.io.load_image(image_file)
#Run the net and examine the top_k results
transformed_image = self.transformer.preprocess('data', image)
self.net.blobs['data'].data[...] = transformed_image
# Forward pass.
detections = self.net.forward()['detection_out']
# Parse the outputs.
det_label = detections[0,0,:,1]
det_conf = detections[0,0,:,2]
det_xmin = detections[0,0,:,3]
det_ymin = detections[0,0,:,4]
det_xmax = detections[0,0,:,5]
det_ymax = detections[0,0,:,6]
# Get detections with confidence higher than 0.6.
top_indices = [i for i, conf in enumerate(det_conf) if conf >= conf_thresh]
top_conf = det_conf[top_indices]
top_label_indices = det_label[top_indices].tolist()
top_labels = get_labelname(self.labelmap, top_label_indices)
top_xmin = det_xmin[top_indices]
top_ymin = det_ymin[top_indices]
top_xmax = det_xmax[top_indices]
top_ymax = det_ymax[top_indices]
result = []
for i in xrange(min(topn, top_conf.shape[0])):
xmin = top_xmin[i] # xmin = int(round(top_xmin[i] * image.shape[1]))
ymin = top_ymin[i] # ymin = int(round(top_ymin[i] * image.shape[0]))
xmax = top_xmax[i] # xmax = int(round(top_xmax[i] * image.shape[1]))
ymax = top_ymax[i] # ymax = int(round(top_ymax[i] * image.shape[0]))
score = top_conf[i]
label = int(top_label_indices[i])
label_name = top_labels[i]
result.append([xmin, ymin, xmax, ymax, label, score, label_name])
return result
def main(args):
'''main '''
detection = CaffeDetection(args.gpu_id,
args.model_def, args.model_weights,
args.image_resize, args.labelmap_file)
result = detection.detect(args.image_file)
print result
img = Image.open(args.image_file)
draw = ImageDraw.Draw(img)
width, height = img.size
print width, height
for item in result:
xmin = int(round(item[0] * width))
ymin = int(round(item[1] * height))
xmax = int(round(item[2] * width))
ymax = int(round(item[3] * height))
draw.rectangle([xmin, ymin, xmax, ymax], outline=(255, 0, 0))
draw.text([xmin, ymin], item[-1] + str(item[-2]), (0, 0, 255))
print item
print [xmin, ymin, xmax, ymax]
print [xmin, ymin], item[-1]
img.save('./testimage/jhydetect_result_DSC00001.jpg')
def parse_args():
'''parse args'''
parser = argparse.ArgumentParser()
parser.add_argument('--gpu_id', type=int, default=0, help='gpu id')
parser.add_argument('--labelmap_file',
default='/home/jhy/caffe-ssd/data/dronedata/labelmap_voc.prototxt')
parser.add_argument('--model_def',
default='/home/jhy/models/VGGNet/jhyDrone/SSD_512x512/deploy.prototxt')
parser.add_argument('--image_resize', default=512, type=int)
parser.add_argument('--model_weights',
default='/home/jhy/models/VGGNet/jhyDrone/SSD_512x512/'
'VGG_jhyDrone_SSD_512x512_iter_10000.caffemodel')
parser.add_argument('--image_file', default='/home/jhy/caffe-ssd/examples/images/ssd_test_image/DSC00001.jpg')
return parser.parse_args()
if __name__ == '__main__':
main(parse_args())
