Created
July 30, 2020 16:43
-
-
Save jinyup100/53c5e542573e46d11e7ed881af66af57 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import os | |
import onnx | |
import torch | |
import torch.nn as nn | |
import torch.nn.functional as F | |
import cv2 | |
# Class for RPN | |
class RPN(nn.Module): | |
"Region Proposal Network" | |
def __init__(self): | |
super(RPN, self).__init__() | |
def forward(self, z_f, x_f): | |
raise NotImplementedError | |
class DepthwiseXCorr(nn.Module): | |
"Depthwise Correlation Layer" | |
def __init__(self, in_channels, hidden, out_channels, kernel_size=3, hidden_kernel_size=5): | |
super(DepthwiseXCorr, self).__init__() | |
self.conv_kernel = nn.Sequential( | |
nn.Conv2d(in_channels, hidden, kernel_size=kernel_size, bias=False), | |
nn.BatchNorm2d(hidden), | |
nn.ReLU(inplace=True), | |
) | |
self.conv_search = nn.Sequential( | |
nn.Conv2d(in_channels, hidden, kernel_size=kernel_size, bias=False), | |
nn.BatchNorm2d(hidden), | |
nn.ReLU(inplace=True), | |
) | |
self.head = nn.Sequential( | |
nn.Conv2d(hidden, hidden, kernel_size=1, bias=False), | |
nn.BatchNorm2d(hidden), | |
nn.ReLU(inplace=True), | |
nn.Conv2d(hidden, out_channels, kernel_size=1) | |
) | |
def forward(self, kernel, search): | |
kernel = self.conv_kernel(kernel) | |
search = self.conv_search(search) | |
feature = xcorr_depthwise(search, kernel) | |
out = self.head(feature) | |
return out | |
class DepthwiseRPN(RPN): | |
def __init__(self, anchor_num=5, in_channels=256, out_channels=256): | |
super(DepthwiseRPN, self).__init__() | |
self.cls = DepthwiseXCorr(in_channels, out_channels, 2 * anchor_num) | |
self.loc = DepthwiseXCorr(in_channels, out_channels, 4 * anchor_num) | |
def forward(self, z_f, x_f): | |
cls = self.cls(z_f, x_f) | |
loc = self.loc(z_f, x_f) | |
return cls, loc | |
class MultiRPN(RPN): | |
def __init__(self, anchor_num, in_channels, weighted=False): | |
super(MultiRPN, self).__init__() | |
self.weighted = weighted | |
for i in range(len(in_channels)): | |
self.add_module('rpn'+str(i+2), | |
DepthwiseRPN(anchor_num, in_channels[i], in_channels[i])) | |
if self.weighted: | |
self.cls_weight = nn.Parameter(torch.ones(len(in_channels))) | |
self.loc_weight = nn.Parameter(torch.ones(len(in_channels))) | |
def forward(self, z_fs, x_fs): | |
cls = [] | |
loc = [] | |
#z_fs = data[0] | |
#x_fs = data[1] | |
rpn2 = self.rpn2 | |
z_f2 = z_fs[0] | |
x_f2 = x_fs[0] | |
c2,l2 = rpn2(z_f2, x_f2) | |
cls.append(c2) | |
loc.append(l2) | |
rpn3 = self.rpn3 | |
z_f3 = z_fs[1] | |
x_f3 = x_fs[1] | |
c3,l3 = rpn3(z_f3, x_f3) | |
cls.append(c3) | |
loc.append(l3) | |
rpn4 = self.rpn4 | |
z_f4 = z_fs[2] | |
x_f4 = x_fs[2] | |
c4,l4 = rpn4(z_f4, x_f4) | |
cls.append(c4) | |
loc.append(l4) | |
if self.weighted: | |
cls_weight = F.softmax(self.cls_weight, 0) | |
loc_weight = F.softmax(self.loc_weight, 0) | |
def avg(lst): | |
return sum(lst) / len(lst) | |
def weighted_avg(lst, weight): | |
s = 0 | |
fixed_len = 3 | |
for i in range(3): | |
s += lst[i] * weight[i] | |
return s | |
if self.weighted: | |
weighted_avg_cls = weighted_avg(cls, cls_weight) | |
weighted_avg_loc = weighted_avg(loc, loc_weight) | |
#clsloc = [weighted_avg_cls, weighted_avg_loc] | |
return weighted_avg_cls, weighted_avg_loc | |
else: | |
avg_cls = avg(cls) | |
avg_loc = avg(loc) | |
#clsloc = [avg_cls, avg_loc] | |
return avg_cls, avg_loc | |
# End of class for RPN | |
def conv3x3(in_planes, out_planes, stride=1, dilation=1): | |
"3x3 convolution with padding" | |
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, | |
padding=dilation, bias=False, dilation=dilation) | |
def xcorr_depthwise(x, kernel): | |
""" | |
Deptwise convolution for input and weights with the same shapes | |
Elementwise multiplication -> GlobalAveragePooling -> scalar mul on (kernel_h * kernel_w) | |
""" | |
batch = kernel.size(0) | |
channel = kernel.size(1) | |
x = x.view(1, batch*channel, x.size(2), x.size(3)) | |
kernel = kernel.view(batch*channel, 1, kernel.size(2), kernel.size(3)) | |
conv = nn.Conv2d(batch*channel, batch*channel, kernel_size=(kernel.size(2), kernel.size(3)), bias=False, groups=batch*channel) | |
conv.weight = nn.Parameter(kernel) | |
out = conv(x) | |
out = out.view(batch, channel, out.size(2), out.size(3)) | |
out = out.detach() | |
return out | |
# Load the target and search | |
z_crop = np.load('numpy_z_crop.npy') | |
x_crop = np.load('numpy_x_crop.npy') | |
# Load the ONNX models | |
backbone_search = cv2.dnn.readNetFromONNX('resnet_search.onnx') | |
backbone_target = cv2.dnn.readNetFromONNX('resnet_target.onnx') | |
neck_1_out_1 = cv2.dnn.readNetFromONNX('neck_1_out_1.onnx') | |
neck_1_out_2 = cv2.dnn.readNetFromONNX('neck_1_out_2.onnx') | |
neck_2_out_1 = cv2.dnn.readNetFromONNX('neck_2_out_1.onnx') | |
neck_2_out_2 = cv2.dnn.readNetFromONNX('neck_2_out_2.onnx') | |
neck_3_out_1 = cv2.dnn.readNetFromONNX('neck_3_out_1.onnx') | |
neck_3_out_2 = cv2.dnn.readNetFromONNX('neck_3_out_2.onnx') | |
rpn_head = cv2.dnn.readNetFromONNX('rpn_head.onnx') | |
# Use the Imported ONNX Models | |
backbone_target.setInput(z_crop) | |
outNames = ['output_1', 'output_2', 'output_3'] | |
zf_1, zf_2, zf_3 = backbone_target.forward(outNames) | |
neck_1_out_1.setInput(zf_1) | |
zf_s_1 = neck_1_out_1.forward() | |
neck_2_out_1.setInput(zf_2) | |
zf_s_2 = neck_2_out_1.forward() | |
neck_3_out_1.setInput(zf_3) | |
zf_s_3 = neck_3_out_1.forward() | |
zf_s = np.stack([zf_s_1, zf_s_2, zf_s_3]) | |
backbone_search.setInput(x_crop) | |
outNames = ['output_1', 'output_2', 'output_3'] | |
xf_1, xf_2, xf_3 = backbone_search.forward(outNames) | |
neck_1_out_2.setInput(xf_1) | |
xf_s_1 = neck_1_out_2.forward() | |
neck_2_out_2.setInput(xf_2) | |
xf_s_2 = neck_2_out_2.forward() | |
neck_3_out_2.setInput(xf_3) | |
xf_s_3 = neck_3_out_2.forward() | |
xf_s = np.stack([xf_s_1, xf_s_2, xf_s_3]) | |
# Outputs from Imported RPN | |
rpn_head.setInput(zf_s, 'input_1') | |
rpn_head.setInput(xf_s, 'input_2') | |
cls = rpn_head.forward('output_1') | |
loc = rpn_head.forward('output_2') | |
print(cls) | |
print(loc) | |
# Outputs from torch RPN | |
torch_rpn_head = MultiRPN(anchor_num=5,in_channels=[256, 256, 256],weighted=False) | |
torch_cls, torch_loc = torch_rpn_head(torch.Tensor(zf_s), torch.Tensor(xf_s)) | |
print(torch_cls) | |
print(torch_loc) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment