| import cv2 as cv | |
| import numpy as np | |
| img = cv.imread('/home/dkurt/Pictures/download.jpeg') | |
| inp = cv.dnn.blobFromImage(img, 0.017, (224, 224), (103.94,116.78,123.68), swapRB=False, crop=False) | |
| net = cv.dnn.readNet('shufflenet_1x_g3_deploy.prototxt', 'shufflenet_1x_g3.caffemodel') | |
| net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV) | |
| net.setInput(inp) | |
| out = net.forward() |
| from math import sqrt | |
| min_scale = 0.2 | |
| max_scale = 0.95 | |
| num_layers = 6 | |
| aspect_ratios = [1.0, 2.0, 0.5, 3.0, 0.333] | |
| image_width = 300 | |
| image_height = 300 | |
| scales = [min_scale + (max_scale - min_scale) * i / (num_layers - 1) for i in range(num_layers)] + [1.0] |
| node { | |
| name: "image_tensor" | |
| op: "Placeholder" | |
| attr { | |
| key: "dtype" | |
| value { | |
| type: DT_UINT8 | |
| } | |
| } | |
| attr { |
| node { | |
| name: "image_tensor" | |
| op: "Placeholder" | |
| attr { | |
| key: "dtype" | |
| value { | |
| type: DT_UINT8 | |
| } | |
| } | |
| attr { |
| node { | |
| name: "image_tensor" | |
| op: "Placeholder" | |
| attr { | |
| key: "dtype" | |
| value { | |
| type: DT_UINT8 | |
| } | |
| } | |
| attr { |
| # http://answers.opencv.org/s/answers/186571 | |
| node { | |
| name: "input_image" | |
| op: "Placeholder" | |
| attr { | |
| key: "dtype" | |
| value { | |
| type: DT_FLOAT | |
| } | |
| } |
| // Wiki page about how to create .pbtxt files: https://github.com/opencv/opencv/wiki/TensorFlow-Object-Detection-API | |
| // This page is referenced to a single script https://github.com/opencv/opencv/blob/master/samples/dnn/tf_text_graph_ssd.py | |
| #include <opencv2/opencv.hpp> | |
| #include <opencv2/dnn.hpp> | |
| using namespace cv; | |
| using namespace dnn; | |
| const char* classes[] = {"background", "person", "bicycle", "car", "motorcycle", | |
| "airplane", "bus", "train", "truck", "boat", "traffic light", "fire hydrant", |
| node { | |
| name: "image_tensor" | |
| op: "Placeholder" | |
| attr { | |
| key: "dtype" | |
| value { | |
| type: DT_UINT8 | |
| } | |
| } | |
| attr { |
| node { | |
| name: "image_tensor" | |
| op: "Placeholder" | |
| } | |
| node { | |
| name: "FeatureExtractor/MobilenetV1/MobilenetV1/Conv2d_0/convolution" | |
| op: "Conv2D" | |
| input: "image_tensor" | |
| input: "FeatureExtractor/MobilenetV1/Conv2d_0/weights" | |
| attr { |
Let's discuss how to deploy deep learning models trained in TensorFlow framework both in TensorFlow and using OpenCV.
This is how we define a network with a single convolution layer followed by ReLU activation function: