对上交代码进行修改，主要将能量机关去掉，添加了同济的PnP位姿解算，但是同济有个四元数，获取IMU部分没有启用，可能导致精度不够。当前还存在反陀螺功能，修改为逻辑和弹道预测相结合，主要在时间关系上进行调整。
This commit is contained in:
232
tools/TrainCNN/backward.py
Executable file
232
tools/TrainCNN/backward.py
Executable file
@@ -0,0 +1,232 @@
|
||||
#!/usr/bin/python3
|
||||
print("Preparing...")
|
||||
import tensorflow as tf
|
||||
import os
|
||||
from tqdm import tqdm
|
||||
import generate
|
||||
import forward
|
||||
import cv2
|
||||
import numpy as np
|
||||
import mvsdk
|
||||
|
||||
print("Finish!")
|
||||
|
||||
|
||||
def save_kernal(fp, val):
|
||||
print(val.shape[2], file=fp)
|
||||
print(val.shape[3], file=fp)
|
||||
print(val.shape[1], file=fp)
|
||||
print(val.shape[0], file=fp)
|
||||
for in_channel in range(val.shape[2]):
|
||||
for out_channel in range(val.shape[3]):
|
||||
for row in range(val.shape[0]):
|
||||
for col in range(val.shape[1]):
|
||||
print(val[row][col][in_channel][out_channel], file=fp)
|
||||
|
||||
|
||||
def save_weight_mat(fp, val):
|
||||
print(val.shape[0], file=fp)
|
||||
print(val.shape[1], file=fp)
|
||||
for row in range(val.shape[0]):
|
||||
for col in range(val.shape[1]):
|
||||
print(val[row][col], file=fp)
|
||||
|
||||
|
||||
def save_bias(fp, val):
|
||||
print(val.shape[0], file=fp)
|
||||
for i in range(val.shape[0]):
|
||||
print(val[i], file=fp)
|
||||
|
||||
|
||||
def save_para(folder, paras, names, info):
|
||||
os.system("mkdir %s/%s" % (folder, info))
|
||||
for para, name in zip(paras, names):
|
||||
fp = open("%s/%s/%s" % (folder, info, name), "w")
|
||||
if name[-1:] == "b":
|
||||
save_bias(fp, para)
|
||||
elif name[:2] == "fc":
|
||||
save_weight_mat(fp, para)
|
||||
elif name[:4] == "conv":
|
||||
save_kernal(fp, para)
|
||||
fp.close()
|
||||
|
||||
|
||||
STEPS = 100000
|
||||
BATCH = 40
|
||||
LEARNING_RATE_BASE = 0.0003
|
||||
LEARNING_RATE_DECAY = 0.99
|
||||
MOVING_AVERAGE_DECAY = 0.99
|
||||
|
||||
|
||||
def train(dataset, show_bar=False):
|
||||
x = tf.placeholder(tf.float32, [None, generate.SRC_ROWS, generate.SRC_COLS, generate.SRC_CHANNELS])
|
||||
y_ = tf.placeholder(tf.float32, [None, forward.OUTPUT_NODES])
|
||||
keep_rate = tf.placeholder(tf.float32)
|
||||
nodes, vars, vars_name = forward.forward(x, 0.01, keep_rate)
|
||||
y = nodes[-1]
|
||||
|
||||
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
|
||||
# ce = tf.nn.weighted_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1), pos_weight=1)
|
||||
cem = tf.reduce_mean(ce)
|
||||
loss = cem + tf.add_n(tf.get_collection("losses"))
|
||||
|
||||
global_step = tf.Variable(0, trainable=False)
|
||||
learning_rate = tf.train.exponential_decay(
|
||||
LEARNING_RATE_BASE,
|
||||
global_step,
|
||||
len(dataset.train_samples) / BATCH,
|
||||
LEARNING_RATE_DECAY,
|
||||
staircase=False)
|
||||
train_step = tf.train.AdamOptimizer(learning_rate).minimize(loss, global_step=global_step)
|
||||
|
||||
ema = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
|
||||
ema_op = ema.apply(tf.trainable_variables())
|
||||
with tf.control_dependencies([train_step, ema_op]):
|
||||
train_op = tf.no_op(name='train')
|
||||
|
||||
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
|
||||
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
|
||||
|
||||
config = tf.ConfigProto(gpu_options=tf.GPUOptions(allow_growth=True))
|
||||
with tf.Session(config=config) as sess:
|
||||
init_op = tf.global_variables_initializer()
|
||||
sess.run(init_op)
|
||||
|
||||
bar = tqdm(range(STEPS), ascii=True, dynamic_ncols=True)
|
||||
for i in bar:
|
||||
images_samples, labels_samples = dataset.sample_train_sets(BATCH, 0.03)
|
||||
|
||||
_, loss_value, step = sess.run(
|
||||
[train_op, loss, global_step],
|
||||
feed_dict={x: images_samples, y_: labels_samples, keep_rate: 0.3}
|
||||
)
|
||||
|
||||
if step % 500 == 0:
|
||||
test_images, test_labels = dataset.sample_test_sets(10000)
|
||||
test_acc, output = sess.run([accuracy, y],
|
||||
feed_dict={x: test_images, y_: test_labels, keep_rate: 1.0})
|
||||
output = np.argmax(output, axis=1)
|
||||
real = np.argmax(test_labels, axis=1)
|
||||
print("=============test-set===============")
|
||||
for n in range(forward.OUTPUT_NODES):
|
||||
print("label: %d, precise: %f, recall: %f" %
|
||||
(n, np.mean(real[output == n] == n), np.mean(output[real == n] == n)))
|
||||
|
||||
train_images, train_labels = dataset.sample_train_sets(10000)
|
||||
train_acc, output = sess.run([accuracy, y],
|
||||
feed_dict={x: train_images, y_: train_labels, keep_rate: 1.0})
|
||||
output = np.argmax(output, axis=1)
|
||||
real = np.argmax(train_labels, axis=1)
|
||||
print("=============train-set===============")
|
||||
for n in range(forward.OUTPUT_NODES):
|
||||
print("label: %d, precise: %f, recall: %f" %
|
||||
(n, np.mean(real[output == n] == n), np.mean(output[real == n] == n)))
|
||||
print("\n")
|
||||
if train_acc >= 0.99 and test_acc >= 0.99:
|
||||
vars_val = sess.run(vars)
|
||||
save_para(
|
||||
"model",
|
||||
vars_val,
|
||||
vars_name,
|
||||
"steps:%d-train_acc:%f-test_acc:%f" % (step, train_acc, test_acc)
|
||||
)
|
||||
bar.set_postfix({"loss": loss_value, "train_acc": train_acc, "test_acc": test_acc})
|
||||
# print("save done!")
|
||||
|
||||
# pred = sess.run(y, feed_dict={x: test_images, keep_rate:1.0})
|
||||
|
||||
# nodes_val = sess.run(nodes, feed_dict={x:test_images})
|
||||
# return vars_val, nodes_val
|
||||
DevList = mvsdk.CameraEnumerateDevice()
|
||||
nDev = len(DevList)
|
||||
if nDev < 1:
|
||||
print("No camera was found!")
|
||||
return
|
||||
|
||||
for i, DevInfo in enumerate(DevList):
|
||||
print("{}: {} {}".format(i, DevInfo.GetFriendlyName(), DevInfo.GetPortType()))
|
||||
i = 0 if nDev == 1 else int(input("Select camera: "))
|
||||
DevInfo = DevList[i]
|
||||
print(DevInfo)
|
||||
|
||||
# 打开相机
|
||||
hCamera = 0
|
||||
try:
|
||||
hCamera = mvsdk.CameraInit(DevInfo, -1, -1)
|
||||
except mvsdk.CameraException as e:
|
||||
print("CameraInit Failed({}): {}".format(e.error_code, e.message))
|
||||
return
|
||||
|
||||
# 获取相机特性描述
|
||||
cap = mvsdk.CameraGetCapability(hCamera)
|
||||
|
||||
# 判断是黑白相机还是彩色相机
|
||||
monoCamera = (cap.sIspCapacity.bMonoSensor != 0)
|
||||
|
||||
# 黑白相机让ISP直接输出MONO数据，而不是扩展成R=G=B的24位灰度
|
||||
if monoCamera:
|
||||
mvsdk.CameraSetIspOutFormat(hCamera, mvsdk.CAMERA_MEDIA_TYPE_MONO8)
|
||||
else:
|
||||
mvsdk.CameraSetIspOutFormat(hCamera, mvsdk.CAMERA_MEDIA_TYPE_BGR8)
|
||||
|
||||
# 相机模式切换成连续采集
|
||||
mvsdk.CameraSetTriggerMode(hCamera, 0)
|
||||
|
||||
# 手动曝光，曝光时间30ms
|
||||
mvsdk.CameraSetAeState(hCamera, 0)
|
||||
mvsdk.CameraSetExposureTime(hCamera, 30 * 1000)
|
||||
|
||||
# 让SDK内部取图线程开始工作
|
||||
mvsdk.CameraPlay(hCamera)
|
||||
|
||||
# 计算RGB buffer所需的大小，这里直接按照相机的最大分辨率来分配
|
||||
FrameBufferSize = cap.sResolutionRange.iWidthMax * cap.sResolutionRange.iHeightMax * (1 if monoCamera else 3)
|
||||
|
||||
# 分配RGB buffer，用来存放ISP输出的图像
|
||||
# 备注：从相机传输到PC端的是RAW数据，在PC端通过软件ISP转为RGB数据（如果是黑白相机就不需要转换格式，但是ISP还有其它处理，所以也需要分配这个buffer）
|
||||
pFrameBuffer = mvsdk.CameraAlignMalloc(FrameBufferSize, 16)
|
||||
|
||||
while (cv2.waitKey(1) & 0xFF) != ord('q'):
|
||||
# 从相机取一帧图片
|
||||
try:
|
||||
pRawData, FrameHead = mvsdk.CameraGetImageBuffer(hCamera, 200)
|
||||
mvsdk.CameraImageProcess(hCamera, pRawData, pFrameBuffer, FrameHead)
|
||||
mvsdk.CameraReleaseImageBuffer(hCamera, pRawData)
|
||||
# 此时图片已经存储在pFrameBuffer中，对于彩色相机pFrameBuffer=RGB数据，黑白相机pFrameBuffer=8位灰度数据
|
||||
# 把pFrameBuffer转换成opencv的图像格式以进行后续算法处理
|
||||
frame_data = (mvsdk.c_ubyte * FrameHead.uBytes).from_address(pFrameBuffer)
|
||||
frame = np.frombuffer(frame_data, dtype=np.uint8)
|
||||
frame = frame.reshape((FrameHead.iHeight, FrameHead.iWidth,
|
||||
1 if FrameHead.uiMediaType == mvsdk.CAMERA_MEDIA_TYPE_MONO8 else 3))
|
||||
|
||||
frame = cv2.resize(frame, (640, 480), interpolation=cv2.INTER_LINEAR)
|
||||
cv2.imshow("Press q to end", frame)
|
||||
if (cv2.waitKey(1) & 0xFF) == ord(' '):
|
||||
roi = cv2.selectROI("roi", frame)
|
||||
roi = frame[roi[1]:roi[1] + roi[3], roi[0]:roi[0] + roi[2]]
|
||||
print(roi)
|
||||
cv2.imshow("box", roi)
|
||||
image = cv2.resize(roi, (48, 36))
|
||||
image = image.astype(np.float32) / 255.0
|
||||
out = sess.run(y, feed_dict={x: [image]})
|
||||
print(out)
|
||||
print(np.argmax(out))
|
||||
|
||||
except mvsdk.CameraException as e:
|
||||
if e.error_code != mvsdk.CAMERA_STATUS_TIME_OUT:
|
||||
print("CameraGetImageBuffer failed({}): {}".format(e.error_code, e.message))
|
||||
|
||||
# 关闭相机
|
||||
mvsdk.CameraUnInit(hCamera)
|
||||
|
||||
# 释放帧缓存
|
||||
mvsdk.CameraAlignFree(pFrameBuffer)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# import os
|
||||
# os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
|
||||
# os.environ["CUDA_VISIBLE_DEVICES"] = "-1"
|
||||
dataset = generate.DataSet("/home/xinyang/Workspace/box_resize")
|
||||
train(dataset, show_bar=True)
|
||||
input("press enter to continue...")
|
||||
94
tools/TrainCNN/cv_grab.py
Normal file
94
tools/TrainCNN/cv_grab.py
Normal file
@@ -0,0 +1,94 @@
|
||||
#coding=utf-8
|
||||
import cv2
|
||||
import numpy as np
|
||||
import mvsdk
|
||||
|
||||
def main_loop():
|
||||
# 枚举相机
|
||||
DevList = mvsdk.CameraEnumerateDevice()
|
||||
nDev = len(DevList)
|
||||
if nDev < 1:
|
||||
print("No camera was found!")
|
||||
return
|
||||
|
||||
for i, DevInfo in enumerate(DevList):
|
||||
print("{}: {} {}".format(i, DevInfo.GetFriendlyName(), DevInfo.GetPortType()))
|
||||
i = 0 if nDev == 1 else int(input("Select camera: "))
|
||||
DevInfo = DevList[i]
|
||||
print(DevInfo)
|
||||
|
||||
# 打开相机
|
||||
hCamera = 0
|
||||
try:
|
||||
hCamera = mvsdk.CameraInit(DevInfo, -1, -1)
|
||||
except mvsdk.CameraException as e:
|
||||
print("CameraInit Failed({}): {}".format(e.error_code, e.message) )
|
||||
return
|
||||
|
||||
# 获取相机特性描述
|
||||
cap = mvsdk.CameraGetCapability(hCamera)
|
||||
|
||||
# 判断是黑白相机还是彩色相机
|
||||
monoCamera = (cap.sIspCapacity.bMonoSensor != 0)
|
||||
|
||||
# 黑白相机让ISP直接输出MONO数据，而不是扩展成R=G=B的24位灰度
|
||||
if monoCamera:
|
||||
mvsdk.CameraSetIspOutFormat(hCamera, mvsdk.CAMERA_MEDIA_TYPE_MONO8)
|
||||
else:
|
||||
mvsdk.CameraSetIspOutFormat(hCamera, mvsdk.CAMERA_MEDIA_TYPE_BGR8)
|
||||
|
||||
# 相机模式切换成连续采集
|
||||
mvsdk.CameraSetTriggerMode(hCamera, 0)
|
||||
|
||||
# 手动曝光，曝光时间30ms
|
||||
mvsdk.CameraSetAeState(hCamera, 0)
|
||||
mvsdk.CameraSetExposureTime(hCamera, 30 * 1000)
|
||||
|
||||
# 让SDK内部取图线程开始工作
|
||||
mvsdk.CameraPlay(hCamera)
|
||||
|
||||
# 计算RGB buffer所需的大小，这里直接按照相机的最大分辨率来分配
|
||||
FrameBufferSize = cap.sResolutionRange.iWidthMax * cap.sResolutionRange.iHeightMax * (1 if monoCamera else 3)
|
||||
|
||||
# 分配RGB buffer，用来存放ISP输出的图像
|
||||
# 备注：从相机传输到PC端的是RAW数据，在PC端通过软件ISP转为RGB数据（如果是黑白相机就不需要转换格式，但是ISP还有其它处理，所以也需要分配这个buffer）
|
||||
pFrameBuffer = mvsdk.CameraAlignMalloc(FrameBufferSize, 16)
|
||||
|
||||
while (cv2.waitKey(1) & 0xFF) != ord('q'):
|
||||
# 从相机取一帧图片
|
||||
try:
|
||||
pRawData, FrameHead = mvsdk.CameraGetImageBuffer(hCamera, 200)
|
||||
mvsdk.CameraImageProcess(hCamera, pRawData, pFrameBuffer, FrameHead)
|
||||
mvsdk.CameraReleaseImageBuffer(hCamera, pRawData)
|
||||
|
||||
# 此时图片已经存储在pFrameBuffer中，对于彩色相机pFrameBuffer=RGB数据，黑白相机pFrameBuffer=8位灰度数据
|
||||
# 把pFrameBuffer转换成opencv的图像格式以进行后续算法处理
|
||||
frame_data = (mvsdk.c_ubyte * FrameHead.uBytes).from_address(pFrameBuffer)
|
||||
frame = np.frombuffer(frame_data, dtype=np.uint8)
|
||||
frame = frame.reshape((FrameHead.iHeight, FrameHead.iWidth, 1 if FrameHead.uiMediaType == mvsdk.CAMERA_MEDIA_TYPE_MONO8 else 3) )
|
||||
|
||||
frame = cv2.resize(frame, (640,480), interpolation = cv2.INTER_LINEAR)
|
||||
cv2.imshow("Press q to end", frame)
|
||||
roi = cv2.selectROI("roi", frame)
|
||||
roi = frame[roi[1]:roi[1]+roi[3], roi[0]:roi[0]+roi[2]]
|
||||
print(roi)
|
||||
cv2.imshow("box", roi)
|
||||
|
||||
|
||||
except mvsdk.CameraException as e:
|
||||
if e.error_code != mvsdk.CAMERA_STATUS_TIME_OUT:
|
||||
print("CameraGetImageBuffer failed({}): {}".format(e.error_code, e.message) )
|
||||
|
||||
# 关闭相机
|
||||
mvsdk.CameraUnInit(hCamera)
|
||||
|
||||
# 释放帧缓存
|
||||
mvsdk.CameraAlignFree(pFrameBuffer)
|
||||
|
||||
def main():
|
||||
try:
|
||||
main_loop()
|
||||
finally:
|
||||
cv2.destroyAllWindows()
|
||||
|
||||
main()
|
||||
114
tools/TrainCNN/forward.py
Normal file
114
tools/TrainCNN/forward.py
Normal file
@@ -0,0 +1,114 @@
|
||||
import tensorflow as tf
|
||||
|
||||
|
||||
def get_weight(shape, regularizer=None):
|
||||
w = tf.Variable(tf.truncated_normal(shape, stddev=0.1))
|
||||
if regularizer is not None:
|
||||
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(regularizer)(w))
|
||||
return w
|
||||
|
||||
|
||||
def get_bias(shape):
|
||||
b = tf.Variable(tf.zeros(shape))
|
||||
return b
|
||||
|
||||
|
||||
def conv2d(x, w):
|
||||
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding="VALID")
|
||||
|
||||
|
||||
def avg_pool_2x2(x):
|
||||
return tf.nn.avg_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="VALID")
|
||||
|
||||
|
||||
def max_pool_2x2(x):
|
||||
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="VALID")
|
||||
|
||||
|
||||
# 第一层卷积核大小
|
||||
CONV1_KERNAL_SIZE = 5
|
||||
|
||||
# 第一层卷积输出通道数
|
||||
CONV1_OUTPUT_CHANNELS = 6
|
||||
|
||||
# 第二层卷积核大小
|
||||
CONV2_KERNAL_SIZE = 3
|
||||
|
||||
# 第二层卷积输出通道数
|
||||
CONV2_OUTPUT_CHANNELS = 10
|
||||
|
||||
# 第三层卷积核大小
|
||||
CONV3_KERNAL_SIZE = 3
|
||||
|
||||
# 第三层卷积输出通道数
|
||||
CONV3_OUTPUT_CHANNELS = 14
|
||||
|
||||
# 第一层全连接宽度
|
||||
FC1_OUTPUT_NODES = 60
|
||||
|
||||
# 第二层全连接宽度（输出标签类型数）
|
||||
FC2_OUTPUT_NODES = 15
|
||||
|
||||
# 输出标签类型数
|
||||
OUTPUT_NODES = FC2_OUTPUT_NODES
|
||||
|
||||
|
||||
def forward(x, regularizer=None, keep_rate=tf.constant(1.0)):
|
||||
vars = []
|
||||
vars_name = []
|
||||
nodes = []
|
||||
|
||||
conv1_w = get_weight(
|
||||
[CONV1_KERNAL_SIZE, CONV1_KERNAL_SIZE, int(x.shape[3]), CONV1_OUTPUT_CHANNELS]
|
||||
)
|
||||
conv1_b = get_bias([CONV1_OUTPUT_CHANNELS])
|
||||
conv1 = tf.nn.relu(tf.nn.bias_add(conv2d(x, conv1_w), conv1_b))
|
||||
pool1 = avg_pool_2x2(conv1)
|
||||
print("conv1: ", conv1.shape)
|
||||
print("pool1: ", pool1.shape)
|
||||
vars.extend([conv1_w, conv1_b])
|
||||
vars_name.extend(["conv1_w", "conv1_b"])
|
||||
nodes.extend([conv1, pool1])
|
||||
|
||||
conv2_w = get_weight(
|
||||
[CONV2_KERNAL_SIZE, CONV2_KERNAL_SIZE, CONV1_OUTPUT_CHANNELS, CONV2_OUTPUT_CHANNELS]
|
||||
)
|
||||
conv2_b = get_bias([CONV2_OUTPUT_CHANNELS])
|
||||
conv2 = tf.nn.relu(tf.nn.bias_add(conv2d(pool1, conv2_w), conv2_b))
|
||||
pool2 = avg_pool_2x2(conv2)
|
||||
print("conv2: ", conv2.shape)
|
||||
vars.extend([conv2_w, conv2_b])
|
||||
vars_name.extend(["conv2_w", "conv2_b"])
|
||||
nodes.extend([conv2, pool2])
|
||||
|
||||
conv3_w = get_weight(
|
||||
[CONV3_KERNAL_SIZE, CONV3_KERNAL_SIZE, CONV2_OUTPUT_CHANNELS, CONV3_OUTPUT_CHANNELS]
|
||||
)
|
||||
conv3_b = get_bias([CONV3_OUTPUT_CHANNELS])
|
||||
conv3 = tf.nn.relu(tf.nn.bias_add(conv2d(pool2, conv3_w), conv3_b))
|
||||
print("conv3: ", conv3.shape)
|
||||
vars.extend([conv3_w, conv3_b])
|
||||
vars_name.extend(["conv3_w", "conv3_b"])
|
||||
nodes.extend([conv3])
|
||||
|
||||
conv_shape = conv3.get_shape().as_list()
|
||||
node = conv_shape[1] * conv_shape[2] * conv_shape[3]
|
||||
reshaped = tf.reshape(conv3, [-1, node])
|
||||
reshaped = tf.nn.dropout(reshaped, keep_rate)
|
||||
print("reshaped: ", reshaped.shape)
|
||||
|
||||
fc1_w = get_weight([node, FC1_OUTPUT_NODES], regularizer)
|
||||
fc1_b = get_bias([FC1_OUTPUT_NODES])
|
||||
fc1 = tf.nn.relu(tf.matmul(reshaped, fc1_w) + fc1_b)
|
||||
vars.extend([fc1_w, fc1_b])
|
||||
vars_name.extend(["fc1_w", "fc1_b"])
|
||||
nodes.extend([fc1])
|
||||
|
||||
fc2_w = get_weight([FC1_OUTPUT_NODES, FC2_OUTPUT_NODES], regularizer)
|
||||
fc2_b = get_bias([FC2_OUTPUT_NODES])
|
||||
fc2 = tf.matmul(fc1, fc2_w) + fc2_b
|
||||
vars.extend([fc2_w, fc2_b])
|
||||
vars_name.extend(["fc2_w", "fc2_b"])
|
||||
nodes.extend([fc2])
|
||||
|
||||
return nodes, vars, vars_name
|
||||
104
tools/TrainCNN/generate.py
Normal file
104
tools/TrainCNN/generate.py
Normal file
@@ -0,0 +1,104 @@
|
||||
import numpy as np
|
||||
import os
|
||||
import cv2
|
||||
import random
|
||||
from tqdm import tqdm
|
||||
from forward import OUTPUT_NODES
|
||||
|
||||
# 原图像行数
|
||||
SRC_ROWS = 36
|
||||
|
||||
# 原图像列数
|
||||
SRC_COLS = 48
|
||||
|
||||
# 原图像通道数
|
||||
SRC_CHANNELS = 3
|
||||
|
||||
|
||||
class DataSet:
|
||||
def __init__(self, folder):
|
||||
self.train_samples = []
|
||||
self.train_labels = []
|
||||
self.test_samples = []
|
||||
self.test_labels = []
|
||||
self.generate_data_sets(folder)
|
||||
|
||||
def file2nparray(self, name):
|
||||
image = cv2.imread(name)
|
||||
image = cv2.resize(image, (SRC_COLS, SRC_ROWS))
|
||||
image = image.astype(np.float32)
|
||||
return image / 255.0
|
||||
|
||||
def id2label(self, id):
|
||||
a = np.zeros([OUTPUT_NODES])
|
||||
a[id] = 1
|
||||
return a[:]
|
||||
|
||||
def generate_data_sets(self, folder):
|
||||
sets = []
|
||||
for i in range(OUTPUT_NODES):
|
||||
dir = "%s/id%d" % (folder, i)
|
||||
files = os.listdir(dir)
|
||||
for file in tqdm(files, postfix={"loading id": i}, dynamic_ncols=True):
|
||||
if file[-3:] == "jpg":
|
||||
sample = self.file2nparray("%s/%s" % (dir, file))
|
||||
label = self.id2label(i)
|
||||
if random.random() < 0.7:
|
||||
self.train_samples.append(sample)
|
||||
self.train_labels.append(label)
|
||||
if i == 0:
|
||||
tmp = sample.copy()
|
||||
tmp = tmp[:, :, ::-1]
|
||||
self.train_samples.append(tmp)
|
||||
self.train_labels.append(label)
|
||||
else:
|
||||
tmp = sample.copy()
|
||||
tmp = 1.2 * tmp
|
||||
tmp = np.where(tmp > 1, 1, tmp)
|
||||
tmp = np.where(tmp < 0, 0, tmp)
|
||||
self.train_samples.append(tmp)
|
||||
self.train_labels.append(label)
|
||||
tmp = sample.copy()
|
||||
tmp = 0.8 * tmp
|
||||
tmp = np.where(tmp > 1, 1, tmp)
|
||||
tmp = np.where(tmp < 0, 0, tmp)
|
||||
self.train_samples.append(tmp)
|
||||
self.train_labels.append(label)
|
||||
else:
|
||||
self.test_samples.append(sample)
|
||||
self.test_labels.append(label)
|
||||
self.train_samples = np.array(self.train_samples)
|
||||
self.train_labels = np.array(self.train_labels)
|
||||
self.test_samples = np.array(self.test_samples)
|
||||
self.test_labels = np.array(self.test_labels)
|
||||
return sets
|
||||
|
||||
def sample_train_sets(self, length, std=0.0):
|
||||
samples = []
|
||||
labels = []
|
||||
for i in range(length):
|
||||
id = random.randint(0, len(self.train_samples) - 1)
|
||||
samples.append(self.train_samples[id])
|
||||
labels.append(self.train_labels[id])
|
||||
samples = np.array(samples).copy()
|
||||
samples += np.random.normal(0, std, samples.shape)
|
||||
labels = np.array(labels)
|
||||
return samples, labels
|
||||
|
||||
def sample_test_sets(self, length, std=0.0):
|
||||
samples = []
|
||||
labels = []
|
||||
for i in range(length):
|
||||
id = random.randint(0, len(self.test_samples) - 1)
|
||||
samples.append(self.test_samples[id])
|
||||
labels.append(self.test_labels[id])
|
||||
samples = np.array(samples).copy()
|
||||
samples += np.random.normal(0, std, samples.shape)
|
||||
labels = np.array(labels)
|
||||
return samples, labels
|
||||
|
||||
def all_train_sets(self, std=0.0):
|
||||
return self.train_samples[:], self.train_labels[:]
|
||||
|
||||
def all_test_sets(self, std=0.0):
|
||||
return self.test_samples[:], self.test_labels[:]
|
||||
111
tools/TrainCNN/grab.py
Normal file
111
tools/TrainCNN/grab.py
Normal file
@@ -0,0 +1,111 @@
|
||||
#coding=utf-8
|
||||
import mvsdk
|
||||
|
||||
def main():
|
||||
# 枚举相机
|
||||
DevList = mvsdk.CameraEnumerateDevice()
|
||||
nDev = len(DevList)
|
||||
if nDev < 1:
|
||||
print("No camera was found!")
|
||||
return
|
||||
|
||||
for i, DevInfo in enumerate(DevList):
|
||||
print("{}: {} {}".format(i, DevInfo.GetFriendlyName(), DevInfo.GetPortType()))
|
||||
i = 0 if nDev == 1 else int(input("Select camera: "))
|
||||
DevInfo = DevList[i]
|
||||
print(DevInfo)
|
||||
|
||||
# 打开相机
|
||||
hCamera = 0
|
||||
try:
|
||||
hCamera = mvsdk.CameraInit(DevInfo, -1, -1)
|
||||
except mvsdk.CameraException as e:
|
||||
print("CameraInit Failed({}): {}".format(e.error_code, e.message) )
|
||||
return
|
||||
|
||||
# 获取相机特性描述
|
||||
cap = mvsdk.CameraGetCapability(hCamera)
|
||||
PrintCapbility(cap)
|
||||
|
||||
# 判断是黑白相机还是彩色相机
|
||||
monoCamera = (cap.sIspCapacity.bMonoSensor != 0)
|
||||
|
||||
# 黑白相机让ISP直接输出MONO数据，而不是扩展成R=G=B的24位灰度
|
||||
if monoCamera:
|
||||
mvsdk.CameraSetIspOutFormat(hCamera, mvsdk.CAMERA_MEDIA_TYPE_MONO8)
|
||||
|
||||
# 相机模式切换成连续采集
|
||||
mvsdk.CameraSetTriggerMode(hCamera, 0)
|
||||
|
||||
# 手动曝光，曝光时间30ms
|
||||
mvsdk.CameraSetAeState(hCamera, 0)
|
||||
mvsdk.CameraSetExposureTime(hCamera, 30 * 1000)
|
||||
|
||||
# 让SDK内部取图线程开始工作
|
||||
mvsdk.CameraPlay(hCamera)
|
||||
|
||||
# 计算RGB buffer所需的大小，这里直接按照相机的最大分辨率来分配
|
||||
FrameBufferSize = cap.sResolutionRange.iWidthMax * cap.sResolutionRange.iHeightMax * (1 if monoCamera else 3)
|
||||
|
||||
# 分配RGB buffer，用来存放ISP输出的图像
|
||||
# 备注：从相机传输到PC端的是RAW数据，在PC端通过软件ISP转为RGB数据（如果是黑白相机就不需要转换格式，但是ISP还有其它处理，所以也需要分配这个buffer）
|
||||
pFrameBuffer = mvsdk.CameraAlignMalloc(FrameBufferSize, 16)
|
||||
|
||||
# 从相机取一帧图片
|
||||
try:
|
||||
pRawData, FrameHead = mvsdk.CameraGetImageBuffer(hCamera, 2000)
|
||||
mvsdk.CameraImageProcess(hCamera, pRawData, pFrameBuffer, FrameHead)
|
||||
mvsdk.CameraReleaseImageBuffer(hCamera, pRawData)
|
||||
|
||||
# 此时图片已经存储在pFrameBuffer中，对于彩色相机pFrameBuffer=RGB数据，黑白相机pFrameBuffer=8位灰度数据
|
||||
# 该示例中我们只是把图片保存到硬盘文件中
|
||||
status = mvsdk.CameraSaveImage(hCamera, "./grab.bmp", pFrameBuffer, FrameHead, mvsdk.FILE_BMP, 100)
|
||||
if status == mvsdk.CAMERA_STATUS_SUCCESS:
|
||||
print("Save image successfully. image_size = {}X{}".format(FrameHead.iWidth, FrameHead.iHeight) )
|
||||
else:
|
||||
print("Save image failed. err={}".format(status) )
|
||||
except mvsdk.CameraException as e:
|
||||
print("CameraGetImageBuffer failed({}): {}".format(e.error_code, e.message) )
|
||||
|
||||
# 关闭相机
|
||||
mvsdk.CameraUnInit(hCamera)
|
||||
|
||||
# 释放帧缓存
|
||||
mvsdk.CameraAlignFree(pFrameBuffer)
|
||||
|
||||
def PrintCapbility(cap):
|
||||
for i in range(cap.iTriggerDesc):
|
||||
desc = cap.pTriggerDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iImageSizeDesc):
|
||||
desc = cap.pImageSizeDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iClrTempDesc):
|
||||
desc = cap.pClrTempDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iMediaTypeDesc):
|
||||
desc = cap.pMediaTypeDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iFrameSpeedDesc):
|
||||
desc = cap.pFrameSpeedDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iPackLenDesc):
|
||||
desc = cap.pPackLenDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iPresetLut):
|
||||
desc = cap.pPresetLutDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iAeAlmSwDesc):
|
||||
desc = cap.pAeAlmSwDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iAeAlmHdDesc):
|
||||
desc = cap.pAeAlmHdDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iBayerDecAlmSwDesc):
|
||||
desc = cap.pBayerDecAlmSwDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
for i in range(cap.iBayerDecAlmHdDesc):
|
||||
desc = cap.pBayerDecAlmHdDesc[i]
|
||||
print("{}: {}".format(desc.iIndex, desc.GetDescription()) )
|
||||
|
||||
main()
|
||||
2344
tools/TrainCNN/mvsdk.py
Normal file
2344
tools/TrainCNN/mvsdk.py
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user