Merge with master
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
This commit is contained in:
Micaela Verucchi
@@ -0,0 +1,83 @@
|
||||
#include<iostream>
|
||||
#include "tkdnn.h"
|
||||
|
||||
const char *i0_bin = "../tests/imuodom/layers/input0.bin";
|
||||
const char *i1_bin = "../tests/imuodom/layers/input1.bin";
|
||||
const char *i2_bin = "../tests/imuodom/layers/input2.bin";
|
||||
const char *o0_bin = "../tests/imuodom/layers/output0.bin";
|
||||
const char *o1_bin = "../tests/imuodom/layers/output1.bin";
|
||||
|
||||
const char *c0_bin = "../tests/imuodom/layers/conv1d_7.bin";
|
||||
const char *c1_bin = "../tests/imuodom/layers/conv1d_8.bin";
|
||||
const char *c2_bin = "../tests/imuodom/layers/conv1d_9.bin";
|
||||
const char *c3_bin = "../tests/imuodom/layers/conv1d_10.bin";
|
||||
const char *c4_bin = "../tests/imuodom/layers/conv1d_11.bin";
|
||||
const char *c5_bin = "../tests/imuodom/layers/conv1d_12.bin";
|
||||
const char *l0_bin = "../tests/imuodom/layers/bidirectional_3.bin";
|
||||
const char *l1_bin = "../tests/imuodom/layers/bidirectional_4.bin";
|
||||
const char *d0_bin = "../tests/imuodom/layers/dense_3.bin";
|
||||
const char *d1_bin = "../tests/imuodom/layers/dense_4.bin";
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tk::dnn::dataDim_t dim0(1, 4, 1, 100);
|
||||
tk::dnn::dataDim_t dim1(1, 3, 1, 100);
|
||||
tk::dnn::dataDim_t dim2(1, 3, 1, 100);
|
||||
|
||||
// Load input
|
||||
dnnType *i0_d, *i1_d, *i2_d;
|
||||
dnnType *i0_h, *i1_h, *i2_h;
|
||||
readBinaryFile(i0_bin, dim0.tot(), &i0_h, &i0_d);
|
||||
readBinaryFile(i1_bin, dim1.tot(), &i1_h, &i1_d);
|
||||
readBinaryFile(i2_bin, dim2.tot(), &i2_h, &i2_d);
|
||||
|
||||
tk::dnn::Network net(dim0);
|
||||
tk::dnn::Input x0 (&net, dim0, i0_d);
|
||||
tk::dnn::Conv2d x0_0(&net, 128, 1, 11, 1, 1, 0, 0, c0_bin);
|
||||
tk::dnn::Conv2d x0_1(&net, 128, 1, 11, 1, 1, 0, 0, c1_bin);
|
||||
tk::dnn::Pooling x0_2(&net, 1, 3, 1, 3, tk::dnn::tkdnnPoolingMode_t::POOLING_MAX);
|
||||
|
||||
tk::dnn::Input x1 (&net, dim1, i1_d);
|
||||
tk::dnn::Conv2d x1_0(&net, 128, 1, 11, 1, 1, 0, 0, c2_bin);
|
||||
tk::dnn::Conv2d x1_1(&net, 128, 1, 11, 1, 1, 0, 0, c3_bin);
|
||||
tk::dnn::Pooling x1_2(&net, 1, 3, 1, 3, tk::dnn::tkdnnPoolingMode_t::POOLING_MAX);
|
||||
|
||||
tk::dnn::Input x2 (&net, dim2, i2_d);
|
||||
tk::dnn::Conv2d x2_0(&net, 128, 1, 11, 1, 1, 0, 0, c4_bin);
|
||||
tk::dnn::Conv2d x2_1(&net, 128, 1, 11, 1, 1, 0, 0, c5_bin);
|
||||
tk::dnn::Pooling x2_2(&net, 1, 3, 1, 3, tk::dnn::tkdnnPoolingMode_t::POOLING_MAX);
|
||||
|
||||
tk::dnn::Layer *concat_l[3] = { &x0_2, &x1_2, &x2_2 };
|
||||
tk::dnn::Route concat (&net, concat_l, 3);
|
||||
|
||||
tk::dnn::LSTM lstm0(&net, 128, true, l0_bin);
|
||||
tk::dnn::LSTM lstm1(&net, 128, false, l1_bin);
|
||||
|
||||
tk::dnn::Dense d0 (&net, 3, d0_bin);
|
||||
|
||||
tk::dnn::Layer *lstm1_l[1] = { &lstm1 };
|
||||
tk::dnn::Route lstm1_link (&net, lstm1_l, 1);
|
||||
tk::dnn::Dense d1 (&net, 4, d1_bin);
|
||||
net.print();
|
||||
|
||||
dnnType *data;
|
||||
tk::dnn::dataDim_t dim;
|
||||
|
||||
TIMER_START
|
||||
// Inference
|
||||
data = net.infer(dim, data);
|
||||
TIMER_STOP
|
||||
|
||||
// Print real test
|
||||
std::cout<<"\n==== CHECK RESULT ====\n";
|
||||
dnnType *out0, *out1;
|
||||
dnnType *out0_h, *out1_h;
|
||||
readBinaryFile(o0_bin, d0.output_dim.tot(), &out0_h, &out0);
|
||||
readBinaryFile(o1_bin, d1.output_dim.tot(), &out1_h, &out1);
|
||||
d0.output_dim.print();
|
||||
checkResult(d0.output_dim.tot(), d0.dstData, out0);
|
||||
d1.output_dim.print();
|
||||
checkResult(d1.output_dim.tot(), d1.dstData, out1);
|
||||
return 0;
|
||||
}
|
||||
@@ -0,0 +1,78 @@
|
||||
import keras
|
||||
from keras.models import load_model
|
||||
import keras.backend.tensorflow_backend as KTF
|
||||
import numpy as np
|
||||
import argparse
|
||||
import tensorflow as tf
|
||||
import os
|
||||
import random
|
||||
import struct
|
||||
from keras.models import Sequential, Model
|
||||
|
||||
def bin_write(f, data):
|
||||
data = data.flatten()
|
||||
fmt = 'f'*len(data)
|
||||
bin = struct.pack(fmt, *data)
|
||||
f.write(bin)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
|
||||
print("DATA FORMAT: ", keras.backend.image_data_format())
|
||||
|
||||
print("Load model: ", "ferrariS1.hdf5")
|
||||
model = load_model("ferrariS1.hdf5")
|
||||
model.summary()
|
||||
|
||||
weights = model.get_weights()
|
||||
|
||||
np.random.seed(2)
|
||||
x_angle = np.random.rand(1,100,4)
|
||||
x_gyro = np.random.rand(1,100,3)
|
||||
x_acc = np.random.rand(1,100,3)
|
||||
|
||||
[yhat_delta_p, yhat_delta_q] = model.predict([x_angle, x_gyro, x_acc], batch_size=1, verbose=1)
|
||||
|
||||
#layer_name = 'dense_4'
|
||||
#intermediate_layer_model = Model(inputs=model.input,
|
||||
# outputs=model.get_layer(layer_name).output)
|
||||
#intermediate_output = intermediate_layer_model.predict([x_angle, x_gyro, x_acc])
|
||||
|
||||
|
||||
x_angle = np.array([x_angle])
|
||||
x_gyro = np.array([x_gyro])
|
||||
x_acc = np.array([x_acc])
|
||||
#intermediate_output = np.array([intermediate_output])
|
||||
|
||||
x_angle = x_angle.transpose(0, 3, 1, 2)
|
||||
x_gyro = x_gyro.transpose(0, 3, 1, 2)
|
||||
x_acc = x_acc.transpose(0, 3, 1, 2)
|
||||
#intermediate_output = intermediate_output.transpose(0, 3, 1, 2)
|
||||
#print("Aggregate:")
|
||||
#print(intermediate_output.tolist())
|
||||
|
||||
print("x0: ", np.shape(x_angle))
|
||||
#print("out: ",np.shape(intermediate_output))
|
||||
|
||||
x_angle = np.array(x_angle.flatten(), dtype=np.float32)
|
||||
x_gyro = np.array(x_gyro.flatten(), dtype=np.float32)
|
||||
x_acc = np.array(x_acc.flatten(), dtype=np.float32)
|
||||
yhat_delta_p = np.array(yhat_delta_p.flatten(), dtype=np.float32)
|
||||
yhat_delta_q = np.array(yhat_delta_q.flatten(), dtype=np.float32)
|
||||
#intermediate_output = np.array(intermediate_output.flatten(), dtype=np.float32)
|
||||
|
||||
|
||||
f = open("layers/input0.bin", mode='wb')
|
||||
bin_write(f, x_angle)
|
||||
f = open("layers/input1.bin", mode='wb')
|
||||
bin_write(f, x_gyro)
|
||||
f = open("layers/input2.bin", mode='wb')
|
||||
bin_write(f, x_acc)
|
||||
f = open("layers/output0.bin", mode='wb')
|
||||
bin_write(f, yhat_delta_p)
|
||||
f = open("layers/output1.bin", mode='wb')
|
||||
bin_write(f, yhat_delta_q)
|
||||
#f = open("layers/output.bin", mode='wb')
|
||||
#bin_write(f, intermediate_output)
|
||||
|
||||
+38
-27
@@ -1,43 +1,54 @@
|
||||
import keras
|
||||
import numpy as np
|
||||
from keras.models import Sequential
|
||||
from keras.layers import Input, Dense, Activation, Flatten, Dropout, ELU, Reshape, Lambda
|
||||
from keras.layers import Input, Dense, Activation, Flatten, Dropout, ELU, Reshape, Lambda, Conv1D
|
||||
from keras.layers import Bidirectional, CuDNNLSTM
|
||||
from keras.layers.convolutional import Convolution2D, Convolution3D
|
||||
from keras.layers.pooling import MaxPooling2D, MaxPooling3D, AveragePooling3D
|
||||
from keras.models import Sequential, Model
|
||||
from keras.layers import Cropping2D
|
||||
import keras.backend.tensorflow_backend as KTF
|
||||
import struct
|
||||
from keras.models import Sequential, Model
|
||||
|
||||
def dense_model():
|
||||
model = Sequential()
|
||||
def bin_write(f, data):
|
||||
data = data.flatten()
|
||||
fmt = 'f'*len(data)
|
||||
bin = struct.pack(fmt, *data)
|
||||
f.write(bin)
|
||||
|
||||
def create_model():
|
||||
x1 = Input((3, 8), name='x1')
|
||||
conv = Conv1D(4, 2)(x1)
|
||||
lstm = Bidirectional(CuDNNLSTM(5, return_sequences=True))(conv)
|
||||
lstm2 = Bidirectional(CuDNNLSTM(5, return_sequences=False))(lstm)
|
||||
model = Model([x1], [lstm2])
|
||||
model.summary()
|
||||
|
||||
model.add(Reshape((10, 10, 1), input_shape=(10, 10)))
|
||||
model.add(Convolution2D(2, (4, 4), subsample=(2, 2),
|
||||
bias_initializer='random_uniform', activation="relu"))
|
||||
model.add(Convolution2D(4, (2, 2), subsample=(1, 1),
|
||||
bias_initializer='random_uniform', activation="relu"))
|
||||
model.add(Flatten())
|
||||
model.add(Dense(4, bias_initializer='random_uniform', activation="relu"))
|
||||
sgd = keras.optimizers.Adam(lr=1e-4, decay=1e-8)
|
||||
model.compile(optimizer=sgd, loss="mse")
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
print "DATA FORMAT: ", keras.backend.image_data_format()
|
||||
print ("DATA FORMAT: ", keras.backend.image_data_format())
|
||||
|
||||
model = dense_model()
|
||||
model.save("net.h5")
|
||||
model = create_model()
|
||||
model.save("net.hdf5")
|
||||
|
||||
grid = np.random.rand(10,10)
|
||||
X = grid[None,:,:]
|
||||
i = np.array(grid.flatten(), dtype=np.float32)
|
||||
print i
|
||||
i.tofile("input.bin", format="f")
|
||||
print "Input: ", X
|
||||
np.random.seed(2)
|
||||
x = np.random.rand(1,1,3,8)
|
||||
r = model.predict( x[0], batch_size=1)
|
||||
|
||||
r = np.array([r])
|
||||
x = x.transpose(0, 3, 1, 2)
|
||||
#r = r.transpose(0, 3, 1, 2)
|
||||
print("in: ", np.shape(x))
|
||||
print("out: ", np.shape(r))
|
||||
print("output: ", r.tolist())
|
||||
|
||||
x = np.array(x.flatten(), dtype=np.float32)
|
||||
f = open("input.bin", mode='wb')
|
||||
bin_write(f, x)
|
||||
|
||||
r = np.array(r.flatten(), dtype=np.float32)
|
||||
f = open("output.bin", mode='wb')
|
||||
bin_write(f, r)
|
||||
|
||||
r = model.predict( X, batch_size=1)
|
||||
print np.shape(r)
|
||||
print "Result: ", r
|
||||
print "Result shape: ", np.shape(r)
|
||||
r.tofile("output.bin", format="f")
|
||||
|
||||
@@ -2,23 +2,21 @@
|
||||
#include "tkdnn.h"
|
||||
|
||||
const char *input_bin = "../tests/simple/input.bin";
|
||||
const char *c0_bin = "../tests/simple/layers/c0.bin";
|
||||
const char *c1_bin = "../tests/simple/layers/c1.bin";
|
||||
const char *d2_bin = "../tests/simple/layers/d2.bin";
|
||||
const char *c0_bin = "../tests/simple/layers/conv1d_1.bin";
|
||||
const char *l1_bin = "../tests/simple/layers/bidirectional_1.bin";
|
||||
const char *l2_bin = "../tests/simple/layers/bidirectional_2.bin";
|
||||
const char *output_bin = "../tests/simple/output.bin";
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tk::dnn::dataDim_t dim(1, 1, 10, 10, 1);
|
||||
tk::dnn::dataDim_t dim(1, 8, 1, 3);
|
||||
tk::dnn::Network net(dim);
|
||||
tk::dnn::Conv2d l0(&net, 2, 4, 4, 2, 2, 0, 0, c0_bin);
|
||||
tk::dnn::Activation l1(&net, CUDNN_ACTIVATION_RELU);
|
||||
tk::dnn::Conv2d l2(&net, 4, 2, 2, 1, 1, 0, 0, c1_bin);
|
||||
tk::dnn::Activation l3(&net, CUDNN_ACTIVATION_RELU);
|
||||
tk::dnn::Flatten l4(&net);
|
||||
tk::dnn::Dense l5(&net, 4, d2_bin);
|
||||
tk::dnn::Activation l6(&net, CUDNN_ACTIVATION_RELU);
|
||||
tk::dnn::Conv2d l0(&net, 4, 1, 2, 1, 1, 0, 0, c0_bin);
|
||||
tk::dnn::LSTM l1(&net, 5, true, l1_bin);
|
||||
tk::dnn::LSTM l2(&net, 5, false, l2_bin);
|
||||
|
||||
net.print();
|
||||
|
||||
// Load input
|
||||
dnnType *data;
|
||||
|
||||
+98
-93
@@ -5,96 +5,89 @@ import numpy as np
|
||||
import argparse
|
||||
import tensorflow as tf
|
||||
import os
|
||||
import msgpack
|
||||
import lmdb
|
||||
import random
|
||||
import struct
|
||||
from keras.models import Sequential, Model
|
||||
|
||||
def export_dense(name, weights, bias):
|
||||
print "######## EXPORT", name, "LAYER ########"
|
||||
print "Original weighs:"
|
||||
print weights
|
||||
print bias, "\n"
|
||||
def bin_write(f, data):
|
||||
data = data.flatten()
|
||||
fmt = 'f'*len(data)
|
||||
bin = struct.pack(fmt, *data)
|
||||
f.write(bin)
|
||||
|
||||
#input, filters
|
||||
I, C = np.shape(weights)
|
||||
B = np.shape(bias)
|
||||
print "w shape: ", I, C
|
||||
print "b shape: ", B
|
||||
def export_layer(name, weights, bias):
|
||||
print ("######## EXPORT", name, "LAYER ########")
|
||||
|
||||
wgs = [ [ j[i] for j in weights ] for i in xrange(C) ]
|
||||
wgs = np.array(wgs, dtype=np.float32)
|
||||
|
||||
print "REPOSITIONED WEIGHTS:"
|
||||
print wgs
|
||||
print("wgs pretranpose: ", np.shape(weights))
|
||||
# convert NHWC to NCHW
|
||||
if(weights.ndim == 4):
|
||||
weights = weights.transpose(3,2,0,1)
|
||||
elif(weights.ndim == 3):
|
||||
weights = weights.transpose(2,1,0)
|
||||
elif(weights.ndim == 2):
|
||||
weights = weights.transpose(1,0)
|
||||
else:
|
||||
print("Ndim", weights.ndim)
|
||||
raise("not implemented with dim" )
|
||||
|
||||
print("weights: ", np.shape(weights))
|
||||
print("bias: ", np.shape(bias))
|
||||
|
||||
weights = np.array(weights.flatten(), dtype=np.float32)
|
||||
bias = np.array(bias, dtype=np.float32)
|
||||
wgs.tofile(name + ".bin", format="f")
|
||||
bias.tofile(name + ".bias.bin", format="f")
|
||||
print "WEIGHTS saved\n"
|
||||
print(len(weights) + len(bias))
|
||||
|
||||
def export_conv2d(name, weights, bias):
|
||||
print "######## EXPORT", name, "LAYER ########"
|
||||
print "Original weighs:"
|
||||
print weights
|
||||
print bias, "\n"
|
||||
|
||||
# height, width, input, filters
|
||||
H, W, N, C = np.shape(weights)
|
||||
B = np.shape(bias)
|
||||
print "w shape: ", N, C, H, W
|
||||
print "b shape: ", B
|
||||
f = open(name + ".bin", mode='wb')
|
||||
bin_write(f, weights)
|
||||
bin_write(f, bias)
|
||||
print ("WEIGHTS saved\n")
|
||||
|
||||
wgs = weights.transpose()
|
||||
wgs = wgs.transpose(0, 1, 3, 2)
|
||||
print "Final shape:", np.shape(wgs)
|
||||
wgs = np.array(wgs.flatten(), dtype=np.float32)
|
||||
|
||||
print "REPOSITIONED WEIGHTS:"
|
||||
print wgs
|
||||
def export_bidir(name, params, paramsb):
|
||||
print ("######## EXPORT", name, "LAYER ########")
|
||||
|
||||
f = open(name + ".bin", mode='wb')
|
||||
|
||||
bias = np.array(bias, dtype=np.float32)
|
||||
|
||||
wgs.tofile(name + ".bin", format="f")
|
||||
bias.tofile(name + ".bias.bin", format="f")
|
||||
print "WEIGHTS saved\n"
|
||||
|
||||
def export_conv3d(name, weights, bias):
|
||||
print "######## EXPORT", name, "LAYER ########"
|
||||
print "Original weighs:"
|
||||
print weights
|
||||
print bias, "\n"
|
||||
|
||||
print np.shape(weights)
|
||||
# height, width, input, thickness, filters
|
||||
H, W, T, N, C = np.shape(weights)
|
||||
B = np.shape(bias)
|
||||
print "w shape: ", T, C, H, W #thickness is number of images for cudnn
|
||||
print "b shape: ", B
|
||||
|
||||
wgs = weights.transpose()
|
||||
wgs = wgs.transpose(0, 1, 4, 3, 2)
|
||||
print "Final shape:", np.shape(wgs)
|
||||
wgs = np.array(wgs.flatten(), dtype=np.float32)
|
||||
|
||||
print "REPOSITIONED WEIGHTS:"
|
||||
print wgs
|
||||
|
||||
bias = np.array(bias, dtype=np.float32)
|
||||
|
||||
wgs.tofile(name + ".bin", format="f")
|
||||
bias.tofile(name + ".bias.bin", format="f")
|
||||
print "WEIGHTS saved\n"
|
||||
|
||||
|
||||
def get_session(gpu_fraction=0.5):
|
||||
gpu_options = tf.GPUOptions(allow_growth=True)
|
||||
#per_process_gpu_memory_fraction=gpu_fraction)
|
||||
return tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
|
||||
print("FORWARD")
|
||||
ker = params[0]
|
||||
rec_ker = params[1]
|
||||
bias = params[2]
|
||||
print ("export kernels: ", np.shape(ker))
|
||||
units = np.shape(ker)[1] // 4
|
||||
bin_write(f, ker[:,:units])
|
||||
bin_write(f, ker[:,units:units*2])
|
||||
bin_write(f, ker[:,units*2:units*3])
|
||||
bin_write(f, ker[:,units*3:])
|
||||
print ("export recurrent kernels: ", np.shape(rec_ker))
|
||||
bin_write(f, rec_ker[:,:units])
|
||||
bin_write(f, rec_ker[:,units:units*2])
|
||||
bin_write(f, rec_ker[:,units*2:units*3])
|
||||
bin_write(f, rec_ker[:,units*3:])
|
||||
print ("export kernels: ", np.shape(ker))
|
||||
bin_write(f, bias)
|
||||
print("WEIGHTS saved\n")
|
||||
|
||||
print("BACKWARD")
|
||||
ker = paramsb[0]
|
||||
rec_ker = paramsb[1]
|
||||
bias = paramsb[2]
|
||||
print ("export kernels: ", np.shape(ker))
|
||||
units = np.shape(ker)[1] // 4
|
||||
bin_write(f, ker[:,:units])
|
||||
bin_write(f, ker[:,units:units*2])
|
||||
bin_write(f, ker[:,units*2:units*3])
|
||||
bin_write(f, ker[:,units*3:])
|
||||
print ("export recurrent kernels: ", np.shape(rec_ker))
|
||||
bin_write(f, rec_ker[:,:units])
|
||||
bin_write(f, rec_ker[:,units:units*2])
|
||||
bin_write(f, rec_ker[:,units*2:units*3])
|
||||
bin_write(f, rec_ker[:,units*3:])
|
||||
print ("export kernels: ", np.shape(ker))
|
||||
bin_write(f, bias)
|
||||
print("WEIGHTS saved\n")
|
||||
|
||||
#https://github.com/fchollet/keras/wiki/Converting-convolution-kernels-from-Theano-to-TensorFlow-and-vice-versa
|
||||
if __name__ == '__main__':
|
||||
KTF.set_session(get_session())
|
||||
print("DATA FORMAT: ", keras.backend.image_data_format())
|
||||
|
||||
parser = argparse.ArgumentParser(description='KERAS WEIGHTS EXPORTER TO CUDNN')
|
||||
parser.add_argument('model',type=str,
|
||||
@@ -103,31 +96,43 @@ if __name__ == '__main__':
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
print "DATA FORMAT: ", keras.backend.image_data_format()
|
||||
print("DATA FORMAT: ", keras.backend.image_data_format())
|
||||
|
||||
print "Load model: ", args.model
|
||||
print("Load model: ", args.model)
|
||||
model = load_model(args.model)
|
||||
model.summary()
|
||||
|
||||
|
||||
weights = model.get_weights()
|
||||
|
||||
ws = np.shape(weights)
|
||||
print "Weights shape:", ws
|
||||
print("Weights shape:", ws)
|
||||
|
||||
if not os.path.exists(args.output):
|
||||
os.makedirs(args.output)
|
||||
|
||||
num = 0
|
||||
|
||||
name_num = 0
|
||||
for l in model.layers:
|
||||
name = l.name
|
||||
if name.startswith("conv3d"):
|
||||
export_conv3d(args.output + "/conv" + str(name_num), weights[num], weights[num+1])
|
||||
elif name.startswith("conv2d"):
|
||||
export_conv2d(args.output + "/conv" + str(name_num), weights[num], weights[num+1])
|
||||
elif name.startswith("dense"):
|
||||
export_dense(args.output + "/dense" + str(name_num), weights[num], weights[num+1])
|
||||
else:
|
||||
print "skip:", name, "has no weights"
|
||||
continue
|
||||
name_num += 1
|
||||
num += 2
|
||||
print("\n\nNAME: ", l.name)
|
||||
print("input: ", l.input_shape, " output: ", l.output_shape)
|
||||
wgs = l.get_weights()
|
||||
print("wgs num: ", len(wgs))
|
||||
|
||||
name = l.name
|
||||
if name.startswith("conv3d"):
|
||||
export_layer(args.output + "/" + name, wgs[0], wgs[1])
|
||||
elif name.startswith("conv2d"):
|
||||
export_layer(args.output + "/" + name, wgs[0], wgs[1])
|
||||
elif name.startswith("conv1d"):
|
||||
export_layer(args.output + "/" + name, wgs[0], wgs[1])
|
||||
elif name.startswith("dense"):
|
||||
export_layer(args.output + "/" + name, wgs[0], wgs[1])
|
||||
elif name.startswith("bidirectional"):
|
||||
wgs = l.forward_layer.get_weights()
|
||||
export_bidir(args.output + "/" + name, l.forward_layer.get_weights(), l.backward_layer.get_weights())
|
||||
else:
|
||||
print ("skip:", name, "has no weights")
|
||||
continue
|
||||
|
||||
|
||||
|
||||
@@ -1,295 +1,23 @@
|
||||
#include<iostream>
|
||||
#include<vector>
|
||||
#include "tkdnn.h"
|
||||
|
||||
const char *input_bin = "../tests/yolo3_berkeley/layers/input.bin";
|
||||
const char *c0_bin = "../tests/yolo3_berkeley/layers/c0.bin";
|
||||
const char *c1_bin = "../tests/yolo3_berkeley/layers/c1.bin";
|
||||
const char *c2_bin = "../tests/yolo3_berkeley/layers/c2.bin";
|
||||
const char *c3_bin = "../tests/yolo3_berkeley/layers/c3.bin";
|
||||
const char *c5_bin = "../tests/yolo3_berkeley/layers/c5.bin";
|
||||
const char *c6_bin = "../tests/yolo3_berkeley/layers/c6.bin";
|
||||
const char *c7_bin = "../tests/yolo3_berkeley/layers/c7.bin";
|
||||
const char *c9_bin = "../tests/yolo3_berkeley/layers/c9.bin";
|
||||
const char *c10_bin = "../tests/yolo3_berkeley/layers/c10.bin";
|
||||
const char *c12_bin = "../tests/yolo3_berkeley/layers/c12.bin";
|
||||
const char *c13_bin = "../tests/yolo3_berkeley/layers/c13.bin";
|
||||
const char *c14_bin = "../tests/yolo3_berkeley/layers/c14.bin";
|
||||
const char *c16_bin = "../tests/yolo3_berkeley/layers/c16.bin";
|
||||
const char *c17_bin = "../tests/yolo3_berkeley/layers/c17.bin";
|
||||
const char *c19_bin = "../tests/yolo3_berkeley/layers/c19.bin";
|
||||
const char *c20_bin = "../tests/yolo3_berkeley/layers/c20.bin";
|
||||
const char *c22_bin = "../tests/yolo3_berkeley/layers/c22.bin";
|
||||
const char *c23_bin = "../tests/yolo3_berkeley/layers/c23.bin";
|
||||
const char *c25_bin = "../tests/yolo3_berkeley/layers/c25.bin";
|
||||
const char *c26_bin = "../tests/yolo3_berkeley/layers/c26.bin";
|
||||
const char *c28_bin = "../tests/yolo3_berkeley/layers/c28.bin";
|
||||
const char *c29_bin = "../tests/yolo3_berkeley/layers/c29.bin";
|
||||
const char *c31_bin = "../tests/yolo3_berkeley/layers/c31.bin";
|
||||
const char *c32_bin = "../tests/yolo3_berkeley/layers/c32.bin";
|
||||
const char *c34_bin = "../tests/yolo3_berkeley/layers/c34.bin";
|
||||
const char *c35_bin = "../tests/yolo3_berkeley/layers/c35.bin";
|
||||
const char *c37_bin = "../tests/yolo3_berkeley/layers/c37.bin";
|
||||
const char *c38_bin = "../tests/yolo3_berkeley/layers/c38.bin";
|
||||
const char *c39_bin = "../tests/yolo3_berkeley/layers/c39.bin";
|
||||
const char *c41_bin = "../tests/yolo3_berkeley/layers/c41.bin";
|
||||
const char *c42_bin = "../tests/yolo3_berkeley/layers/c42.bin";
|
||||
const char *c44_bin = "../tests/yolo3_berkeley/layers/c44.bin";
|
||||
const char *c45_bin = "../tests/yolo3_berkeley/layers/c45.bin";
|
||||
const char *c47_bin = "../tests/yolo3_berkeley/layers/c47.bin";
|
||||
const char *c48_bin = "../tests/yolo3_berkeley/layers/c48.bin";
|
||||
const char *c50_bin = "../tests/yolo3_berkeley/layers/c50.bin";
|
||||
const char *c51_bin = "../tests/yolo3_berkeley/layers/c51.bin";
|
||||
const char *c53_bin = "../tests/yolo3_berkeley/layers/c53.bin";
|
||||
const char *c54_bin = "../tests/yolo3_berkeley/layers/c54.bin";
|
||||
const char *c56_bin = "../tests/yolo3_berkeley/layers/c56.bin";
|
||||
const char *c57_bin = "../tests/yolo3_berkeley/layers/c57.bin";
|
||||
const char *c59_bin = "../tests/yolo3_berkeley/layers/c59.bin";
|
||||
const char *c60_bin = "../tests/yolo3_berkeley/layers/c60.bin";
|
||||
const char *c62_bin = "../tests/yolo3_berkeley/layers/c62.bin";
|
||||
const char *c63_bin = "../tests/yolo3_berkeley/layers/c63.bin";
|
||||
const char *c64_bin = "../tests/yolo3_berkeley/layers/c64.bin";
|
||||
const char *c66_bin = "../tests/yolo3_berkeley/layers/c66.bin";
|
||||
const char *c67_bin = "../tests/yolo3_berkeley/layers/c67.bin";
|
||||
const char *c69_bin = "../tests/yolo3_berkeley/layers/c69.bin";
|
||||
const char *c70_bin = "../tests/yolo3_berkeley/layers/c70.bin";
|
||||
const char *c72_bin = "../tests/yolo3_berkeley/layers/c72.bin";
|
||||
const char *c73_bin = "../tests/yolo3_berkeley/layers/c73.bin";
|
||||
const char *c75_bin = "../tests/yolo3_berkeley/layers/c75.bin";
|
||||
const char *c76_bin = "../tests/yolo3_berkeley/layers/c76.bin";
|
||||
const char *c77_bin = "../tests/yolo3_berkeley/layers/c77.bin";
|
||||
const char *c78_bin = "../tests/yolo3_berkeley/layers/c78.bin";
|
||||
const char *c79_bin = "../tests/yolo3_berkeley/layers/c79.bin";
|
||||
const char *c80_bin = "../tests/yolo3_berkeley/layers/c80.bin";
|
||||
const char *c81_bin = "../tests/yolo3_berkeley/layers/c81.bin";
|
||||
const char *g82_bin = "../tests/yolo3_berkeley/layers/g82.bin";
|
||||
const char *c84_bin = "../tests/yolo3_berkeley/layers/c84.bin";
|
||||
const char *c87_bin = "../tests/yolo3_berkeley/layers/c87.bin";
|
||||
const char *c88_bin = "../tests/yolo3_berkeley/layers/c88.bin";
|
||||
const char *c89_bin = "../tests/yolo3_berkeley/layers/c89.bin";
|
||||
const char *c90_bin = "../tests/yolo3_berkeley/layers/c90.bin";
|
||||
const char *c91_bin = "../tests/yolo3_berkeley/layers/c91.bin";
|
||||
const char *c92_bin = "../tests/yolo3_berkeley/layers/c92.bin";
|
||||
const char *c93_bin = "../tests/yolo3_berkeley/layers/c93.bin";
|
||||
const char *g94_bin = "../tests/yolo3_berkeley/layers/g94.bin";
|
||||
const char *c96_bin = "../tests/yolo3_berkeley/layers/c96.bin";
|
||||
const char *c99_bin = "../tests/yolo3_berkeley/layers/c99.bin";
|
||||
const char *c100_bin = "../tests/yolo3_berkeley/layers/c100.bin";
|
||||
const char *c101_bin = "../tests/yolo3_berkeley/layers/c101.bin";
|
||||
const char *c102_bin = "../tests/yolo3_berkeley/layers/c102.bin";
|
||||
const char *c103_bin = "../tests/yolo3_berkeley/layers/c103.bin";
|
||||
const char *c104_bin = "../tests/yolo3_berkeley/layers/c104.bin";
|
||||
const char *c105_bin = "../tests/yolo3_berkeley/layers/c105.bin";
|
||||
const char *g106_bin = "../tests/yolo3_berkeley/layers/g106.bin";
|
||||
const char *output_bins[3] = {
|
||||
"../tests/yolo3_berkeley/debug/layer82_out.bin",
|
||||
"../tests/yolo3_berkeley/debug/layer94_out.bin",
|
||||
"../tests/yolo3_berkeley/debug/layer106_out.bin"
|
||||
};
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tk::dnn::dataDim_t dim(1, 3, 320, 544, 1);
|
||||
tk::dnn::Network net(dim);
|
||||
|
||||
tk::dnn::Conv2d c0 (&net, 32, 3, 3, 1, 1, 1, 1, c0_bin, true);
|
||||
tk::dnn::Activation a0 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c1 (&net, 64, 3, 3, 2, 2, 1, 1, c1_bin, true);
|
||||
tk::dnn::Activation a1 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c2 (&net, 32, 1, 1, 1, 1, 0, 0, c2_bin, true);
|
||||
tk::dnn::Activation a2 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c3 (&net, 64, 3, 3, 1, 1, 1, 1, c3_bin, true);
|
||||
tk::dnn::Activation a3 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s4 (&net, &a1);
|
||||
tk::dnn::Conv2d c5 (&net, 128, 3, 3, 2, 2, 1, 1, c5_bin, true);
|
||||
tk::dnn::Activation a5 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c6 (&net, 64, 1, 1, 1, 1, 0, 0, c6_bin, true);
|
||||
tk::dnn::Activation a6 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c7 (&net, 128, 3, 3, 1, 1, 1, 1, c7_bin, true);
|
||||
tk::dnn::Activation a7 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s8 (&net, &a5);
|
||||
tk::dnn::Conv2d c9 (&net, 64, 1, 1, 1, 1, 0, 0, c9_bin, true);
|
||||
tk::dnn::Activation a9 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c10 (&net, 128, 3, 3, 1, 1, 1, 1, c10_bin, true);
|
||||
tk::dnn::Activation a10 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s11 (&net, &s8);
|
||||
// create yolo3 model
|
||||
std::string bin_path = "../tests/yolo3_berkeley";
|
||||
int classes = 10;
|
||||
tk::dnn::Yolo *yolo [3];
|
||||
#include "models/Yolo3.h"
|
||||
|
||||
tk::dnn::Conv2d c12 (&net, 256, 3, 3, 2, 2, 1, 1, c12_bin, true);
|
||||
tk::dnn::Activation a12 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c13 (&net, 128, 1, 1, 1, 1, 0, 0, c13_bin, true);
|
||||
tk::dnn::Activation a13 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c14 (&net, 256, 3, 3, 1, 1, 1, 1, c14_bin, true);
|
||||
tk::dnn::Activation a14 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s15 (&net, &a12);
|
||||
|
||||
tk::dnn::Conv2d c16 (&net, 128, 1, 1, 1, 1, 0, 0, c16_bin, true);
|
||||
tk::dnn::Activation a16 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c17 (&net, 256, 3, 3, 1, 1, 1, 1, c17_bin, true);
|
||||
tk::dnn::Activation a17 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s18 (&net, &s15);
|
||||
tk::dnn::Conv2d c19 (&net, 128, 1, 1, 1, 1, 0, 0, c19_bin, true);
|
||||
tk::dnn::Activation a19 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c20 (&net, 256, 3, 3, 1, 1, 1, 1, c20_bin, true);
|
||||
tk::dnn::Activation a20 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s21 (&net, &s18);
|
||||
tk::dnn::Conv2d c22 (&net, 128, 1, 1, 1, 1, 0, 0, c22_bin, true);
|
||||
tk::dnn::Activation a22 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c23 (&net, 256, 3, 3, 1, 1, 1, 1, c23_bin, true);
|
||||
tk::dnn::Activation a23 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s24 (&net, &s21);
|
||||
tk::dnn::Conv2d c25 (&net, 128, 1, 1, 1, 1, 0, 0, c25_bin, true);
|
||||
tk::dnn::Activation a25 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c26 (&net, 256, 3, 3, 1, 1, 1, 1, c26_bin, true);
|
||||
tk::dnn::Activation a26 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s27 (&net, &s24);
|
||||
tk::dnn::Conv2d c28 (&net, 128, 1, 1, 1, 1, 0, 0, c28_bin, true);
|
||||
tk::dnn::Activation a28 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c29 (&net, 256, 3, 3, 1, 1, 1, 1, c29_bin, true);
|
||||
tk::dnn::Activation a29 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s30 (&net, &s27);
|
||||
tk::dnn::Conv2d c31 (&net, 128, 1, 1, 1, 1, 0, 0, c31_bin, true);
|
||||
tk::dnn::Activation a31 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c32 (&net, 256, 3, 3, 1, 1, 1, 1, c32_bin, true);
|
||||
tk::dnn::Activation a32 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s33 (&net, &s30);
|
||||
tk::dnn::Conv2d c34 (&net, 128, 1, 1, 1, 1, 0, 0, c34_bin, true);
|
||||
tk::dnn::Activation a34 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c35 (&net, 256, 3, 3, 1, 1, 1, 1, c35_bin, true);
|
||||
tk::dnn::Activation a35 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s36 (&net, &s33);
|
||||
|
||||
tk::dnn::Conv2d c37 (&net, 512, 3, 3, 2, 2, 1, 1, c37_bin, true);
|
||||
tk::dnn::Activation a37 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c38 (&net, 256, 1, 1, 1, 1, 0, 0, c38_bin, true);
|
||||
tk::dnn::Activation a38 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c39 (&net, 512, 3, 3, 1, 1, 1, 1, c39_bin, true);
|
||||
tk::dnn::Activation a39 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s40 (&net, &a37);
|
||||
|
||||
tk::dnn::Conv2d c41 (&net, 256, 1, 1, 1, 1, 0, 0, c41_bin, true);
|
||||
tk::dnn::Activation a41 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c42 (&net, 512, 3, 3, 1, 1, 1, 1, c42_bin, true);
|
||||
tk::dnn::Activation a42 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s43 (&net, &s40);
|
||||
tk::dnn::Conv2d c44 (&net, 256, 1, 1, 1, 1, 0, 0, c44_bin, true);
|
||||
tk::dnn::Activation a44 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c45 (&net, 512, 3, 3, 1, 1, 1, 1, c45_bin, true);
|
||||
tk::dnn::Activation a45 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s46 (&net, &s43);
|
||||
tk::dnn::Conv2d c47 (&net, 256, 1, 1, 1, 1, 0, 0, c47_bin, true);
|
||||
tk::dnn::Activation a47 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c48 (&net, 512, 3, 3, 1, 1, 1, 1, c48_bin, true);
|
||||
tk::dnn::Activation a48 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s49 (&net, &s46);
|
||||
tk::dnn::Conv2d c50 (&net, 256, 1, 1, 1, 1, 0, 0, c50_bin, true);
|
||||
tk::dnn::Activation a50 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c51 (&net, 512, 3, 3, 1, 1, 1, 1, c51_bin, true);
|
||||
tk::dnn::Activation a51 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s52 (&net, &s49);
|
||||
tk::dnn::Conv2d c53 (&net, 256, 1, 1, 1, 1, 0, 0, c53_bin, true);
|
||||
tk::dnn::Activation a53 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c54 (&net, 512, 3, 3, 1, 1, 1, 1, c54_bin, true);
|
||||
tk::dnn::Activation a54 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s55 (&net, &s52);
|
||||
tk::dnn::Conv2d c56 (&net, 256, 1, 1, 1, 1, 0, 0, c56_bin, true);
|
||||
tk::dnn::Activation a56 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c57 (&net, 512, 3, 3, 1, 1, 1, 1, c57_bin, true);
|
||||
tk::dnn::Activation a57 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s58 (&net, &s55);
|
||||
tk::dnn::Conv2d c59 (&net, 256, 1, 1, 1, 1, 0, 0, c59_bin, true);
|
||||
tk::dnn::Activation a59 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c60 (&net, 512, 3, 3, 1, 1, 1, 1, c60_bin, true);
|
||||
tk::dnn::Activation a60 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s61 (&net, &s58);
|
||||
|
||||
tk::dnn::Conv2d c62 (&net,1024, 3, 3, 2, 2, 1, 1, c62_bin, true);
|
||||
tk::dnn::Activation a62 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c63 (&net, 512, 1, 1, 1, 1, 0, 0, c63_bin, true);
|
||||
tk::dnn::Activation a63 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c64 (&net,1024, 3, 3, 1, 1, 1, 1, c64_bin, true);
|
||||
tk::dnn::Activation a64 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s65 (&net, &a62);
|
||||
|
||||
tk::dnn::Conv2d c66 (&net, 512, 1, 1, 1, 1, 0, 0, c66_bin, true);
|
||||
tk::dnn::Activation a66 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c67 (&net,1024, 3, 3, 1, 1, 1, 1, c67_bin, true);
|
||||
tk::dnn::Activation a67 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s68 (&net, &s65);
|
||||
|
||||
tk::dnn::Conv2d c69 (&net, 512, 1, 1, 1, 1, 0, 0, c69_bin, true);
|
||||
tk::dnn::Activation a69 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c70 (&net,1024, 3, 3, 1, 1, 1, 1, c70_bin, true);
|
||||
tk::dnn::Activation a70 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s71 (&net, &s68);
|
||||
|
||||
tk::dnn::Conv2d c72 (&net, 512, 1, 1, 1, 1, 0, 0, c72_bin, true);
|
||||
tk::dnn::Activation a72 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c73 (&net,1024, 3, 3, 1, 1, 1, 1, c73_bin, true);
|
||||
tk::dnn::Activation a73 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s74 (&net, &s71);
|
||||
|
||||
tk::dnn::Conv2d c75 (&net, 512, 1, 1, 1, 1, 0, 0, c75_bin, true);
|
||||
tk::dnn::Activation a75 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c76 (&net,1024, 3, 3, 1, 1, 1, 1, c76_bin, true);
|
||||
tk::dnn::Activation a76 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c77 (&net, 512, 1, 1, 1, 1, 0, 0, c77_bin, true);
|
||||
tk::dnn::Activation a77 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c78 (&net,1024, 3, 3, 1, 1, 1, 1, c78_bin, true);
|
||||
tk::dnn::Activation a78 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c79 (&net, 512, 1, 1, 1, 1, 0, 0, c79_bin, true);
|
||||
tk::dnn::Activation a79 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c80 (&net,1024, 3, 3, 1, 1, 1, 1, c80_bin, true);
|
||||
tk::dnn::Activation a80 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c81 (&net, 45, 1, 1, 1, 1, 0, 0, c81_bin, false);
|
||||
tk::dnn::Yolo yolo0 (&net, 10, 3, g82_bin);
|
||||
|
||||
tk::dnn::Layer *m83_layers[1] = { &a79 };
|
||||
tk::dnn::Route m83 (&net, m83_layers, 1);
|
||||
tk::dnn::Conv2d c84 (&net, 256, 1, 1, 1, 1, 0, 0, c84_bin, true);
|
||||
tk::dnn::Activation a84 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Upsample u85 (&net, 2);
|
||||
|
||||
tk::dnn::Layer *m86_layers[2] = { &u85, &s61 };
|
||||
tk::dnn::Route m86 (&net, m86_layers, 2);
|
||||
tk::dnn::Conv2d c87 (&net, 256, 1, 1, 1, 1, 0, 0, c87_bin, true);
|
||||
tk::dnn::Activation a87 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c88 (&net, 512, 3, 3, 1, 1, 1, 1, c88_bin, true);
|
||||
tk::dnn::Activation a88 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c89 (&net, 256, 1, 1, 1, 1, 0, 0, c89_bin, true);
|
||||
tk::dnn::Activation a89 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c90 (&net, 512, 3, 3, 1, 1, 1, 1, c90_bin, true);
|
||||
tk::dnn::Activation a90 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c91 (&net, 256, 1, 1, 1, 1, 0, 0, c91_bin, true);
|
||||
tk::dnn::Activation a91 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
|
||||
tk::dnn::Conv2d c92 (&net, 512, 3, 3, 1, 1, 1, 1, c92_bin, true);
|
||||
tk::dnn::Activation a92 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c93 (&net, 45, 1, 1, 1, 1, 0, 0, c93_bin, false);
|
||||
tk::dnn::Yolo yolo1 (&net, 10, 3, g94_bin);
|
||||
|
||||
tk::dnn::Layer *m95_layers[1] = { &a91 };
|
||||
tk::dnn::Route m95 (&net, m95_layers, 1);
|
||||
tk::dnn::Conv2d c96 (&net, 128, 1, 1, 1, 1, 0, 0, c96_bin, true);
|
||||
tk::dnn::Activation a96 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Upsample u97 (&net, 2);
|
||||
|
||||
tk::dnn::Layer *m98_layers[2] = { &u97, &s36 };
|
||||
tk::dnn::Route m98 (&net, m98_layers, 2);
|
||||
tk::dnn::Conv2d c99 (&net, 128, 1, 1, 1, 1, 0, 0, c99_bin, true);
|
||||
tk::dnn::Activation a99 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c100 (&net, 256, 3, 3, 1, 1, 1, 1, c100_bin, true);
|
||||
tk::dnn::Activation a100 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c101 (&net, 128, 1, 1, 1, 1, 0, 0, c101_bin, true);
|
||||
tk::dnn::Activation a101 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c102 (&net, 256, 3, 3, 1, 1, 1, 1, c102_bin, true);
|
||||
tk::dnn::Activation a102 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c103 (&net, 128, 1, 1, 1, 1, 0, 0, c103_bin, true);
|
||||
tk::dnn::Activation a103 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
|
||||
tk::dnn::Conv2d c104 (&net, 256, 3, 3, 1, 1, 1, 1, c104_bin, true);
|
||||
tk::dnn::Activation a104 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c105 (&net, 45, 1, 1, 1, 1, 0, 0, c105_bin, false);
|
||||
tk::dnn::Yolo yolo2 (&net, 10, 3, g106_bin);
|
||||
// fill classes names
|
||||
for(int i=0; i<3; i++) {
|
||||
yolo[i]->classesNames = {"person", "car", "truck", "bus", "motor", "bike", "rider", "traffic light", "traffic sign", "train"};
|
||||
}
|
||||
|
||||
// Load input
|
||||
dnnType *data;
|
||||
@@ -304,9 +32,7 @@ int main() {
|
||||
|
||||
// the network have 3 outputs
|
||||
tk::dnn::dataDim_t out_dim[3];
|
||||
out_dim[0] = yolo0.output_dim;
|
||||
out_dim[1] = yolo1.output_dim;
|
||||
out_dim[2] = yolo2.output_dim;
|
||||
for(int i=0; i<3; i++) out_dim[i] = yolo[i]->output_dim;
|
||||
dnnType *cudnn_out[3], *rt_out[3];
|
||||
|
||||
tk::dnn::dataDim_t dim1 = dim; //input dim
|
||||
@@ -317,18 +43,13 @@ int main() {
|
||||
TIMER_STOP
|
||||
dim1.print();
|
||||
}
|
||||
cudnn_out[0] = yolo0.dstData;
|
||||
cudnn_out[1] = yolo1.dstData;
|
||||
cudnn_out[2] = yolo2.dstData;
|
||||
|
||||
for(int i=0; i<3; i++) cudnn_out[i] = yolo[i]->dstData;
|
||||
|
||||
printCenteredTitle(" compute detections ", '=', 30);
|
||||
TIMER_START
|
||||
int ndets = 0;
|
||||
int classes = yolo0.classes;
|
||||
tk::dnn::Yolo::detection *dets = tk::dnn::Yolo::allocateDetections(tk::dnn::Yolo::MAX_DETECTIONS, classes);
|
||||
yolo0.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
yolo1.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
yolo2.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
for(int i=0; i<3; i++) yolo[i]->computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
tk::dnn::Yolo::mergeDetections(dets, ndets, classes);
|
||||
|
||||
for(int j=0; j<ndets; j++) {
|
||||
@@ -356,9 +77,7 @@ int main() {
|
||||
TIMER_STOP
|
||||
dim2.print();
|
||||
}
|
||||
rt_out[0] = (dnnType*)netRT.buffersRT[1];
|
||||
rt_out[1] = (dnnType*)netRT.buffersRT[2];
|
||||
rt_out[2] = (dnnType*)netRT.buffersRT[3];
|
||||
for(int i=0; i<3; i++) rt_out[i] = (dnnType*)netRT.buffersRT[i+1];
|
||||
|
||||
for(int i=0; i<3; i++) {
|
||||
printCenteredTitle((std::string(" YOLO ") + std::to_string(i) + " CHECK RESULTS ").c_str(), '=', 30);
|
||||
|
||||
@@ -1,295 +1,18 @@
|
||||
#include<iostream>
|
||||
#include<vector>
|
||||
#include "tkdnn.h"
|
||||
|
||||
const char *input_bin = "../tests/yolo3_coco4/layers/input.bin";
|
||||
const char *c0_bin = "../tests/yolo3_coco4/layers/c0.bin";
|
||||
const char *c1_bin = "../tests/yolo3_coco4/layers/c1.bin";
|
||||
const char *c2_bin = "../tests/yolo3_coco4/layers/c2.bin";
|
||||
const char *c3_bin = "../tests/yolo3_coco4/layers/c3.bin";
|
||||
const char *c5_bin = "../tests/yolo3_coco4/layers/c5.bin";
|
||||
const char *c6_bin = "../tests/yolo3_coco4/layers/c6.bin";
|
||||
const char *c7_bin = "../tests/yolo3_coco4/layers/c7.bin";
|
||||
const char *c9_bin = "../tests/yolo3_coco4/layers/c9.bin";
|
||||
const char *c10_bin = "../tests/yolo3_coco4/layers/c10.bin";
|
||||
const char *c12_bin = "../tests/yolo3_coco4/layers/c12.bin";
|
||||
const char *c13_bin = "../tests/yolo3_coco4/layers/c13.bin";
|
||||
const char *c14_bin = "../tests/yolo3_coco4/layers/c14.bin";
|
||||
const char *c16_bin = "../tests/yolo3_coco4/layers/c16.bin";
|
||||
const char *c17_bin = "../tests/yolo3_coco4/layers/c17.bin";
|
||||
const char *c19_bin = "../tests/yolo3_coco4/layers/c19.bin";
|
||||
const char *c20_bin = "../tests/yolo3_coco4/layers/c20.bin";
|
||||
const char *c22_bin = "../tests/yolo3_coco4/layers/c22.bin";
|
||||
const char *c23_bin = "../tests/yolo3_coco4/layers/c23.bin";
|
||||
const char *c25_bin = "../tests/yolo3_coco4/layers/c25.bin";
|
||||
const char *c26_bin = "../tests/yolo3_coco4/layers/c26.bin";
|
||||
const char *c28_bin = "../tests/yolo3_coco4/layers/c28.bin";
|
||||
const char *c29_bin = "../tests/yolo3_coco4/layers/c29.bin";
|
||||
const char *c31_bin = "../tests/yolo3_coco4/layers/c31.bin";
|
||||
const char *c32_bin = "../tests/yolo3_coco4/layers/c32.bin";
|
||||
const char *c34_bin = "../tests/yolo3_coco4/layers/c34.bin";
|
||||
const char *c35_bin = "../tests/yolo3_coco4/layers/c35.bin";
|
||||
const char *c37_bin = "../tests/yolo3_coco4/layers/c37.bin";
|
||||
const char *c38_bin = "../tests/yolo3_coco4/layers/c38.bin";
|
||||
const char *c39_bin = "../tests/yolo3_coco4/layers/c39.bin";
|
||||
const char *c41_bin = "../tests/yolo3_coco4/layers/c41.bin";
|
||||
const char *c42_bin = "../tests/yolo3_coco4/layers/c42.bin";
|
||||
const char *c44_bin = "../tests/yolo3_coco4/layers/c44.bin";
|
||||
const char *c45_bin = "../tests/yolo3_coco4/layers/c45.bin";
|
||||
const char *c47_bin = "../tests/yolo3_coco4/layers/c47.bin";
|
||||
const char *c48_bin = "../tests/yolo3_coco4/layers/c48.bin";
|
||||
const char *c50_bin = "../tests/yolo3_coco4/layers/c50.bin";
|
||||
const char *c51_bin = "../tests/yolo3_coco4/layers/c51.bin";
|
||||
const char *c53_bin = "../tests/yolo3_coco4/layers/c53.bin";
|
||||
const char *c54_bin = "../tests/yolo3_coco4/layers/c54.bin";
|
||||
const char *c56_bin = "../tests/yolo3_coco4/layers/c56.bin";
|
||||
const char *c57_bin = "../tests/yolo3_coco4/layers/c57.bin";
|
||||
const char *c59_bin = "../tests/yolo3_coco4/layers/c59.bin";
|
||||
const char *c60_bin = "../tests/yolo3_coco4/layers/c60.bin";
|
||||
const char *c62_bin = "../tests/yolo3_coco4/layers/c62.bin";
|
||||
const char *c63_bin = "../tests/yolo3_coco4/layers/c63.bin";
|
||||
const char *c64_bin = "../tests/yolo3_coco4/layers/c64.bin";
|
||||
const char *c66_bin = "../tests/yolo3_coco4/layers/c66.bin";
|
||||
const char *c67_bin = "../tests/yolo3_coco4/layers/c67.bin";
|
||||
const char *c69_bin = "../tests/yolo3_coco4/layers/c69.bin";
|
||||
const char *c70_bin = "../tests/yolo3_coco4/layers/c70.bin";
|
||||
const char *c72_bin = "../tests/yolo3_coco4/layers/c72.bin";
|
||||
const char *c73_bin = "../tests/yolo3_coco4/layers/c73.bin";
|
||||
const char *c75_bin = "../tests/yolo3_coco4/layers/c75.bin";
|
||||
const char *c76_bin = "../tests/yolo3_coco4/layers/c76.bin";
|
||||
const char *c77_bin = "../tests/yolo3_coco4/layers/c77.bin";
|
||||
const char *c78_bin = "../tests/yolo3_coco4/layers/c78.bin";
|
||||
const char *c79_bin = "../tests/yolo3_coco4/layers/c79.bin";
|
||||
const char *c80_bin = "../tests/yolo3_coco4/layers/c80.bin";
|
||||
const char *c81_bin = "../tests/yolo3_coco4/layers/c81.bin";
|
||||
const char *g82_bin = "../tests/yolo3_coco4/layers/g82.bin";
|
||||
const char *c84_bin = "../tests/yolo3_coco4/layers/c84.bin";
|
||||
const char *c87_bin = "../tests/yolo3_coco4/layers/c87.bin";
|
||||
const char *c88_bin = "../tests/yolo3_coco4/layers/c88.bin";
|
||||
const char *c89_bin = "../tests/yolo3_coco4/layers/c89.bin";
|
||||
const char *c90_bin = "../tests/yolo3_coco4/layers/c90.bin";
|
||||
const char *c91_bin = "../tests/yolo3_coco4/layers/c91.bin";
|
||||
const char *c92_bin = "../tests/yolo3_coco4/layers/c92.bin";
|
||||
const char *c93_bin = "../tests/yolo3_coco4/layers/c93.bin";
|
||||
const char *g94_bin = "../tests/yolo3_coco4/layers/g94.bin";
|
||||
const char *c96_bin = "../tests/yolo3_coco4/layers/c96.bin";
|
||||
const char *c99_bin = "../tests/yolo3_coco4/layers/c99.bin";
|
||||
const char *c100_bin = "../tests/yolo3_coco4/layers/c100.bin";
|
||||
const char *c101_bin = "../tests/yolo3_coco4/layers/c101.bin";
|
||||
const char *c102_bin = "../tests/yolo3_coco4/layers/c102.bin";
|
||||
const char *c103_bin = "../tests/yolo3_coco4/layers/c103.bin";
|
||||
const char *c104_bin = "../tests/yolo3_coco4/layers/c104.bin";
|
||||
const char *c105_bin = "../tests/yolo3_coco4/layers/c105.bin";
|
||||
const char *g106_bin = "../tests/yolo3_coco4/layers/g106.bin";
|
||||
const char *output_bins[3] = {
|
||||
"../tests/yolo3_coco4/debug/layer82_out.bin",
|
||||
"../tests/yolo3_coco4/debug/layer94_out.bin",
|
||||
"../tests/yolo3_coco4/debug/layer106_out.bin"
|
||||
};
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tk::dnn::dataDim_t dim(1, 3, 416, 416, 1);
|
||||
tk::dnn::Network net(dim);
|
||||
|
||||
tk::dnn::Conv2d c0 (&net, 32, 3, 3, 1, 1, 1, 1, c0_bin, true);
|
||||
tk::dnn::Activation a0 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c1 (&net, 64, 3, 3, 2, 2, 1, 1, c1_bin, true);
|
||||
tk::dnn::Activation a1 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c2 (&net, 32, 1, 1, 1, 1, 0, 0, c2_bin, true);
|
||||
tk::dnn::Activation a2 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c3 (&net, 64, 3, 3, 1, 1, 1, 1, c3_bin, true);
|
||||
tk::dnn::Activation a3 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s4 (&net, &a1);
|
||||
tk::dnn::Conv2d c5 (&net, 128, 3, 3, 2, 2, 1, 1, c5_bin, true);
|
||||
tk::dnn::Activation a5 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c6 (&net, 64, 1, 1, 1, 1, 0, 0, c6_bin, true);
|
||||
tk::dnn::Activation a6 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c7 (&net, 128, 3, 3, 1, 1, 1, 1, c7_bin, true);
|
||||
tk::dnn::Activation a7 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s8 (&net, &a5);
|
||||
tk::dnn::Conv2d c9 (&net, 64, 1, 1, 1, 1, 0, 0, c9_bin, true);
|
||||
tk::dnn::Activation a9 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c10 (&net, 128, 3, 3, 1, 1, 1, 1, c10_bin, true);
|
||||
tk::dnn::Activation a10 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s11 (&net, &s8);
|
||||
|
||||
tk::dnn::Conv2d c12 (&net, 256, 3, 3, 2, 2, 1, 1, c12_bin, true);
|
||||
tk::dnn::Activation a12 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c13 (&net, 128, 1, 1, 1, 1, 0, 0, c13_bin, true);
|
||||
tk::dnn::Activation a13 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c14 (&net, 256, 3, 3, 1, 1, 1, 1, c14_bin, true);
|
||||
tk::dnn::Activation a14 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s15 (&net, &a12);
|
||||
|
||||
tk::dnn::Conv2d c16 (&net, 128, 1, 1, 1, 1, 0, 0, c16_bin, true);
|
||||
tk::dnn::Activation a16 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c17 (&net, 256, 3, 3, 1, 1, 1, 1, c17_bin, true);
|
||||
tk::dnn::Activation a17 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s18 (&net, &s15);
|
||||
tk::dnn::Conv2d c19 (&net, 128, 1, 1, 1, 1, 0, 0, c19_bin, true);
|
||||
tk::dnn::Activation a19 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c20 (&net, 256, 3, 3, 1, 1, 1, 1, c20_bin, true);
|
||||
tk::dnn::Activation a20 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s21 (&net, &s18);
|
||||
tk::dnn::Conv2d c22 (&net, 128, 1, 1, 1, 1, 0, 0, c22_bin, true);
|
||||
tk::dnn::Activation a22 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c23 (&net, 256, 3, 3, 1, 1, 1, 1, c23_bin, true);
|
||||
tk::dnn::Activation a23 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s24 (&net, &s21);
|
||||
tk::dnn::Conv2d c25 (&net, 128, 1, 1, 1, 1, 0, 0, c25_bin, true);
|
||||
tk::dnn::Activation a25 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c26 (&net, 256, 3, 3, 1, 1, 1, 1, c26_bin, true);
|
||||
tk::dnn::Activation a26 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s27 (&net, &s24);
|
||||
tk::dnn::Conv2d c28 (&net, 128, 1, 1, 1, 1, 0, 0, c28_bin, true);
|
||||
tk::dnn::Activation a28 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c29 (&net, 256, 3, 3, 1, 1, 1, 1, c29_bin, true);
|
||||
tk::dnn::Activation a29 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s30 (&net, &s27);
|
||||
tk::dnn::Conv2d c31 (&net, 128, 1, 1, 1, 1, 0, 0, c31_bin, true);
|
||||
tk::dnn::Activation a31 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c32 (&net, 256, 3, 3, 1, 1, 1, 1, c32_bin, true);
|
||||
tk::dnn::Activation a32 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s33 (&net, &s30);
|
||||
tk::dnn::Conv2d c34 (&net, 128, 1, 1, 1, 1, 0, 0, c34_bin, true);
|
||||
tk::dnn::Activation a34 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c35 (&net, 256, 3, 3, 1, 1, 1, 1, c35_bin, true);
|
||||
tk::dnn::Activation a35 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s36 (&net, &s33);
|
||||
|
||||
tk::dnn::Conv2d c37 (&net, 512, 3, 3, 2, 2, 1, 1, c37_bin, true);
|
||||
tk::dnn::Activation a37 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c38 (&net, 256, 1, 1, 1, 1, 0, 0, c38_bin, true);
|
||||
tk::dnn::Activation a38 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c39 (&net, 512, 3, 3, 1, 1, 1, 1, c39_bin, true);
|
||||
tk::dnn::Activation a39 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s40 (&net, &a37);
|
||||
|
||||
tk::dnn::Conv2d c41 (&net, 256, 1, 1, 1, 1, 0, 0, c41_bin, true);
|
||||
tk::dnn::Activation a41 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c42 (&net, 512, 3, 3, 1, 1, 1, 1, c42_bin, true);
|
||||
tk::dnn::Activation a42 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s43 (&net, &s40);
|
||||
tk::dnn::Conv2d c44 (&net, 256, 1, 1, 1, 1, 0, 0, c44_bin, true);
|
||||
tk::dnn::Activation a44 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c45 (&net, 512, 3, 3, 1, 1, 1, 1, c45_bin, true);
|
||||
tk::dnn::Activation a45 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s46 (&net, &s43);
|
||||
tk::dnn::Conv2d c47 (&net, 256, 1, 1, 1, 1, 0, 0, c47_bin, true);
|
||||
tk::dnn::Activation a47 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c48 (&net, 512, 3, 3, 1, 1, 1, 1, c48_bin, true);
|
||||
tk::dnn::Activation a48 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s49 (&net, &s46);
|
||||
tk::dnn::Conv2d c50 (&net, 256, 1, 1, 1, 1, 0, 0, c50_bin, true);
|
||||
tk::dnn::Activation a50 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c51 (&net, 512, 3, 3, 1, 1, 1, 1, c51_bin, true);
|
||||
tk::dnn::Activation a51 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s52 (&net, &s49);
|
||||
tk::dnn::Conv2d c53 (&net, 256, 1, 1, 1, 1, 0, 0, c53_bin, true);
|
||||
tk::dnn::Activation a53 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c54 (&net, 512, 3, 3, 1, 1, 1, 1, c54_bin, true);
|
||||
tk::dnn::Activation a54 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s55 (&net, &s52);
|
||||
tk::dnn::Conv2d c56 (&net, 256, 1, 1, 1, 1, 0, 0, c56_bin, true);
|
||||
tk::dnn::Activation a56 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c57 (&net, 512, 3, 3, 1, 1, 1, 1, c57_bin, true);
|
||||
tk::dnn::Activation a57 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s58 (&net, &s55);
|
||||
tk::dnn::Conv2d c59 (&net, 256, 1, 1, 1, 1, 0, 0, c59_bin, true);
|
||||
tk::dnn::Activation a59 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c60 (&net, 512, 3, 3, 1, 1, 1, 1, c60_bin, true);
|
||||
tk::dnn::Activation a60 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s61 (&net, &s58);
|
||||
|
||||
tk::dnn::Conv2d c62 (&net,1024, 3, 3, 2, 2, 1, 1, c62_bin, true);
|
||||
tk::dnn::Activation a62 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c63 (&net, 512, 1, 1, 1, 1, 0, 0, c63_bin, true);
|
||||
tk::dnn::Activation a63 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c64 (&net,1024, 3, 3, 1, 1, 1, 1, c64_bin, true);
|
||||
tk::dnn::Activation a64 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s65 (&net, &a62);
|
||||
|
||||
tk::dnn::Conv2d c66 (&net, 512, 1, 1, 1, 1, 0, 0, c66_bin, true);
|
||||
tk::dnn::Activation a66 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c67 (&net,1024, 3, 3, 1, 1, 1, 1, c67_bin, true);
|
||||
tk::dnn::Activation a67 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s68 (&net, &s65);
|
||||
|
||||
tk::dnn::Conv2d c69 (&net, 512, 1, 1, 1, 1, 0, 0, c69_bin, true);
|
||||
tk::dnn::Activation a69 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c70 (&net,1024, 3, 3, 1, 1, 1, 1, c70_bin, true);
|
||||
tk::dnn::Activation a70 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s71 (&net, &s68);
|
||||
|
||||
tk::dnn::Conv2d c72 (&net, 512, 1, 1, 1, 1, 0, 0, c72_bin, true);
|
||||
tk::dnn::Activation a72 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c73 (&net,1024, 3, 3, 1, 1, 1, 1, c73_bin, true);
|
||||
tk::dnn::Activation a73 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Shortcut s74 (&net, &s71);
|
||||
|
||||
tk::dnn::Conv2d c75 (&net, 512, 1, 1, 1, 1, 0, 0, c75_bin, true);
|
||||
tk::dnn::Activation a75 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c76 (&net,1024, 3, 3, 1, 1, 1, 1, c76_bin, true);
|
||||
tk::dnn::Activation a76 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c77 (&net, 512, 1, 1, 1, 1, 0, 0, c77_bin, true);
|
||||
tk::dnn::Activation a77 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c78 (&net,1024, 3, 3, 1, 1, 1, 1, c78_bin, true);
|
||||
tk::dnn::Activation a78 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c79 (&net, 512, 1, 1, 1, 1, 0, 0, c79_bin, true);
|
||||
tk::dnn::Activation a79 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c80 (&net,1024, 3, 3, 1, 1, 1, 1, c80_bin, true);
|
||||
tk::dnn::Activation a80 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c81 (&net, 27, 1, 1, 1, 1, 0, 0, c81_bin, false);
|
||||
tk::dnn::Yolo yolo0 (&net, 4, 3, g82_bin);
|
||||
|
||||
tk::dnn::Layer *m83_layers[1] = { &a79 };
|
||||
tk::dnn::Route m83 (&net, m83_layers, 1);
|
||||
tk::dnn::Conv2d c84 (&net, 256, 1, 1, 1, 1, 0, 0, c84_bin, true);
|
||||
tk::dnn::Activation a84 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Upsample u85 (&net, 2);
|
||||
|
||||
tk::dnn::Layer *m86_layers[2] = { &u85, &s61 };
|
||||
tk::dnn::Route m86 (&net, m86_layers, 2);
|
||||
tk::dnn::Conv2d c87 (&net, 256, 1, 1, 1, 1, 0, 0, c87_bin, true);
|
||||
tk::dnn::Activation a87 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c88 (&net, 512, 3, 3, 1, 1, 1, 1, c88_bin, true);
|
||||
tk::dnn::Activation a88 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c89 (&net, 256, 1, 1, 1, 1, 0, 0, c89_bin, true);
|
||||
tk::dnn::Activation a89 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c90 (&net, 512, 3, 3, 1, 1, 1, 1, c90_bin, true);
|
||||
tk::dnn::Activation a90 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c91 (&net, 256, 1, 1, 1, 1, 0, 0, c91_bin, true);
|
||||
tk::dnn::Activation a91 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
|
||||
tk::dnn::Conv2d c92 (&net, 512, 3, 3, 1, 1, 1, 1, c92_bin, true);
|
||||
tk::dnn::Activation a92 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c93 (&net, 27, 1, 1, 1, 1, 0, 0, c93_bin, false);
|
||||
tk::dnn::Yolo yolo1 (&net, 4, 3, g94_bin);
|
||||
|
||||
tk::dnn::Layer *m95_layers[1] = { &a91 };
|
||||
tk::dnn::Route m95 (&net, m95_layers, 1);
|
||||
tk::dnn::Conv2d c96 (&net, 128, 1, 1, 1, 1, 0, 0, c96_bin, true);
|
||||
tk::dnn::Activation a96 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Upsample u97 (&net, 2);
|
||||
|
||||
tk::dnn::Layer *m98_layers[2] = { &u97, &s36 };
|
||||
tk::dnn::Route m98 (&net, m98_layers, 2);
|
||||
tk::dnn::Conv2d c99 (&net, 128, 1, 1, 1, 1, 0, 0, c99_bin, true);
|
||||
tk::dnn::Activation a99 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c100 (&net, 256, 3, 3, 1, 1, 1, 1, c100_bin, true);
|
||||
tk::dnn::Activation a100 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c101 (&net, 128, 1, 1, 1, 1, 0, 0, c101_bin, true);
|
||||
tk::dnn::Activation a101 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c102 (&net, 256, 3, 3, 1, 1, 1, 1, c102_bin, true);
|
||||
tk::dnn::Activation a102 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c103 (&net, 128, 1, 1, 1, 1, 0, 0, c103_bin, true);
|
||||
tk::dnn::Activation a103 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
|
||||
tk::dnn::Conv2d c104 (&net, 256, 3, 3, 1, 1, 1, 1, c104_bin, true);
|
||||
tk::dnn::Activation a104 (&net, tk::dnn::ACTIVATION_LEAKY);
|
||||
tk::dnn::Conv2d c105 (&net, 27, 1, 1, 1, 1, 0, 0, c105_bin, false);
|
||||
tk::dnn::Yolo yolo2 (&net, 4, 3, g106_bin);
|
||||
// create yolo3 model
|
||||
std::string bin_path = "../tests/yolo3_coco4";
|
||||
int classes = 4;
|
||||
tk::dnn::Yolo *yolo [3];
|
||||
#include "models/Yolo3.h"
|
||||
|
||||
// Load input
|
||||
dnnType *data;
|
||||
@@ -304,9 +27,7 @@ int main() {
|
||||
|
||||
// the network have 3 outputs
|
||||
tk::dnn::dataDim_t out_dim[3];
|
||||
out_dim[0] = yolo0.output_dim;
|
||||
out_dim[1] = yolo1.output_dim;
|
||||
out_dim[2] = yolo2.output_dim;
|
||||
for(int i=0; i<3; i++) out_dim[i] = yolo[i]->output_dim;
|
||||
dnnType *cudnn_out[3], *rt_out[3];
|
||||
|
||||
tk::dnn::dataDim_t dim1 = dim; //input dim
|
||||
@@ -317,18 +38,13 @@ int main() {
|
||||
TIMER_STOP
|
||||
dim1.print();
|
||||
}
|
||||
cudnn_out[0] = yolo0.dstData;
|
||||
cudnn_out[1] = yolo1.dstData;
|
||||
cudnn_out[2] = yolo2.dstData;
|
||||
|
||||
for(int i=0; i<3; i++) cudnn_out[i] = yolo[i]->dstData;
|
||||
|
||||
printCenteredTitle(" compute detections ", '=', 30);
|
||||
TIMER_START
|
||||
int ndets = 0;
|
||||
int classes = yolo0.classes;
|
||||
tk::dnn::Yolo::detection *dets = tk::dnn::Yolo::allocateDetections(tk::dnn::Yolo::MAX_DETECTIONS, classes);
|
||||
yolo0.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
yolo1.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
yolo2.computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
for(int i=0; i<3; i++) yolo[i]->computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
tk::dnn::Yolo::mergeDetections(dets, ndets, classes);
|
||||
|
||||
for(int j=0; j<ndets; j++) {
|
||||
@@ -356,9 +72,7 @@ int main() {
|
||||
TIMER_STOP
|
||||
dim2.print();
|
||||
}
|
||||
rt_out[0] = (dnnType*)netRT.buffersRT[1];
|
||||
rt_out[1] = (dnnType*)netRT.buffersRT[2];
|
||||
rt_out[2] = (dnnType*)netRT.buffersRT[3];
|
||||
for(int i=0; i<3; i++) rt_out[i] = (dnnType*)netRT.buffersRT[i+1];
|
||||
|
||||
for(int i=0; i<3; i++) {
|
||||
printCenteredTitle((std::string(" YOLO ") + std::to_string(i) + " CHECK RESULTS ").c_str(), '=', 30);
|
||||
|
||||
@@ -0,0 +1,785 @@
|
||||
[net]
|
||||
# Testing
|
||||
#batch=1
|
||||
#subdivisions=1
|
||||
# Training
|
||||
batch=32
|
||||
subdivisions=8
|
||||
width=544
|
||||
height=320
|
||||
channels=1
|
||||
momentum=0.9
|
||||
decay=0.0005
|
||||
angle=0
|
||||
saturation = 1.5
|
||||
exposure = 1.5
|
||||
hue=.1
|
||||
|
||||
learning_rate=0.001
|
||||
burn_in=1000
|
||||
max_batches = 20000
|
||||
policy=steps
|
||||
steps=8000,9000
|
||||
scales=.1,.1
|
||||
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=32
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
# Downsample
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=3
|
||||
stride=2
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=32
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
# Downsample
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=3
|
||||
stride=2
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
# Downsample
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=2
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
# Downsample
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=2
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
# Downsample
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=2
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[shortcut]
|
||||
from=-3
|
||||
activation=linear
|
||||
|
||||
######################
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
filters=24
|
||||
activation=linear
|
||||
|
||||
[yolo]
|
||||
mask = 6,7,8
|
||||
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
|
||||
classes=3
|
||||
num=9
|
||||
jitter=.3
|
||||
ignore_thresh = .5
|
||||
truth_thresh = 1
|
||||
random=0
|
||||
|
||||
[route]
|
||||
layers = -4
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[upsample]
|
||||
stride=2
|
||||
|
||||
[route]
|
||||
layers = -1, 61
|
||||
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=512
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=512
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=512
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
filters=24
|
||||
activation=linear
|
||||
|
||||
[yolo]
|
||||
mask = 3,4,5
|
||||
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
|
||||
classes=3
|
||||
num=9
|
||||
jitter=.3
|
||||
ignore_thresh = .5
|
||||
truth_thresh = 1
|
||||
random=0
|
||||
|
||||
[route]
|
||||
layers = -4
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[upsample]
|
||||
stride=2
|
||||
|
||||
[route]
|
||||
layers = -1, 36
|
||||
|
||||
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=256
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=256
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=256
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
filters=24
|
||||
activation=linear
|
||||
|
||||
[yolo]
|
||||
mask = 0,1,2
|
||||
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
|
||||
classes=3
|
||||
num=9
|
||||
jitter=.3
|
||||
ignore_thresh = .5
|
||||
truth_thresh = 1
|
||||
random=0
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
#include<iostream>
|
||||
#include<vector>
|
||||
#include "tkdnn.h"
|
||||
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tk::dnn::dataDim_t dim(1, 1, 320, 544, 1);
|
||||
tk::dnn::Network net(dim);
|
||||
|
||||
// create yolo3 model
|
||||
std::string bin_path = "../tests/yolo3_flir";
|
||||
int classes = 3;
|
||||
tk::dnn::Yolo *yolo [3];
|
||||
#include "models/Yolo3.h"
|
||||
|
||||
// fill classes names
|
||||
for(int i=0; i<3; i++) {
|
||||
yolo[i]->classesNames = {"person", "bike", "car"};
|
||||
}
|
||||
|
||||
// Load input
|
||||
dnnType *data;
|
||||
dnnType *input_h;
|
||||
readBinaryFile(input_bin, dim.tot(), &input_h, &data);
|
||||
|
||||
//print network model
|
||||
net.print();
|
||||
|
||||
//convert network to tensorRT
|
||||
tk::dnn::NetworkRT netRT(&net, "yolo3_flir.rt");
|
||||
|
||||
// the network have 3 outputs
|
||||
tk::dnn::dataDim_t out_dim[3];
|
||||
for(int i=0; i<3; i++) out_dim[i] = yolo[i]->output_dim;
|
||||
dnnType *cudnn_out[3], *rt_out[3];
|
||||
|
||||
tk::dnn::dataDim_t dim1 = dim; //input dim
|
||||
printCenteredTitle(" CUDNN inference ", '=', 30); {
|
||||
dim1.print();
|
||||
TIMER_START
|
||||
net.infer(dim1, data);
|
||||
TIMER_STOP
|
||||
dim1.print();
|
||||
}
|
||||
for(int i=0; i<3; i++) cudnn_out[i] = yolo[i]->dstData;
|
||||
|
||||
printCenteredTitle(" compute detections ", '=', 30);
|
||||
TIMER_START
|
||||
int ndets = 0;
|
||||
tk::dnn::Yolo::detection *dets = tk::dnn::Yolo::allocateDetections(tk::dnn::Yolo::MAX_DETECTIONS, classes);
|
||||
for(int i=0; i<3; i++) yolo[i]->computeDetections(dets, ndets, net.input_dim.w, net.input_dim.h, 0.5);
|
||||
tk::dnn::Yolo::mergeDetections(dets, ndets, classes);
|
||||
|
||||
for(int j=0; j<ndets; j++) {
|
||||
tk::dnn::Yolo::box b = dets[j].bbox;
|
||||
int x0 = (b.x-b.w/2.);
|
||||
int x1 = (b.x+b.w/2.);
|
||||
int y0 = (b.y-b.h/2.);
|
||||
int y1 = (b.y+b.h/2.);
|
||||
|
||||
int cl = 0;
|
||||
for(int c = 0; c < classes; ++c){
|
||||
float prob = dets[j].prob[c];
|
||||
if(prob > 0)
|
||||
cl = c;
|
||||
}
|
||||
std::cout<<cl<<": "<<x0<<" "<<y0<<" "<<x1<<" "<<y1<<"\n";
|
||||
}
|
||||
TIMER_STOP
|
||||
|
||||
tk::dnn::dataDim_t dim2 = dim;
|
||||
printCenteredTitle(" TENSORRT inference ", '=', 30); {
|
||||
dim2.print();
|
||||
TIMER_START
|
||||
netRT.infer(dim2, data);
|
||||
TIMER_STOP
|
||||
dim2.print();
|
||||
}
|
||||
for(int i=0; i<3; i++) rt_out[i] = (dnnType*)netRT.buffersRT[i+1];
|
||||
|
||||
for(int i=0; i<3; i++) {
|
||||
printCenteredTitle((std::string(" YOLO ") + std::to_string(i) + " CHECK RESULTS ").c_str(), '=', 30);
|
||||
dnnType *out, *out_h;
|
||||
int odim = out_dim[i].tot();
|
||||
readBinaryFile(output_bins[i], odim, &out_h, &out);
|
||||
std::cout<<"CUDNN vs correct"; checkResult(odim, cudnn_out[i], out);
|
||||
std::cout<<"TRT vs correct"; checkResult(odim, rt_out[i], out);
|
||||
std::cout<<"CUDNN vs TRT "; checkResult(odim, cudnn_out[i], rt_out[i]);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user