object-detection

问题 I am using Tensorflow Object Detection API(github.com/tensorflow/models/tree/master/object_detection) with one object detection task. Right now I am having problem on serving the detection model I trained with Tensorflow Serving(tensorflow.github.io/serving/). 1. The first issue I am encountering is about exporting the model to servable files. The object detection api kindly included the export script so that I am able to convert ckpt files to pb files with variables. However, the output

问题 I am using Tensorflow's object detection framework. Training and evaluation jobs are going well, but in tensorboard I am only able to see 10 images for the evaluation job. Is there a way to increase this number to look at more images? I tried changing the config file: eval_config: { num_examples: 1000 max_evals: 50 } eval_input_reader: { tf_record_input_reader { input_path: "xxx/eval.record" } label_map_path: "xxx/label_map.pbtxt" shuffle: false num_readers: 1 } I thought the max_eval

问题 I am trying to make a prediction using Tensorflow Object Detection API on Google COLAB . Already I successfully completed the training process and Export Inference Graph task. But Problem is when I am going to make a new prediction it's throwing some error log. cannot connect to X server Now I am unable to make a new prediction. Some portion of my error log: totalMemory: 11.17GiB freeMemory: 6.65GiB 2019-02-07 15:08:38.398219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding

问题 I am trying to make a prediction using Tensorflow Object Detection API on Google COLAB . Already I successfully completed the training process and Export Inference Graph task. But Problem is when I am going to make a new prediction it's throwing some error log. cannot connect to X server Now I am unable to make a new prediction. Some portion of my error log: totalMemory: 11.17GiB freeMemory: 6.65GiB 2019-02-07 15:08:38.398219: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding

问题 This is a more general question about the Tensorflow Object-Detection API. I am using this API, to be more concrete I fine-tune a model to my dataset. According to the description of the API, I use the model_main.py function to retrain a model from a given checkpoint/frozen graph. However, it is not clear for me how the fine-tuning is working within the API. Does a re-initialization of the last layer happen automatically or do I have to implement something like ? In the README files I did not

问题 I have a question regarding data augmentation for training the deep neural network for object detection. I have quite limited data set (nearly 300 images). I augmented the data by rotating each image from 0-360 degrees with stepsize of 15 degree. Consequently I got 24 rotated images out of just one. So in total, I got around 7200 images. Then I drew bounding box around the object of interest in each augmented image. Does it seem to be a reasonable approach to enhance the data? Best Regards

问题 I don't know if this the right stackexchange forum where to ask this question, please let me know if this is not the case. I'm developing an application which given an input image containing a painting as input, it is able to tell you the title of the painting. An analogous case is: given an input image containing a building, the returned result is the name of the building. What kind of application is this? On first impact, I would say something like "image classification". I'm not an expert

问题 I`m trying to run the model I did in TensorFlow Object Detection API with my own dataset, but when running script I get such error: python object_detection/detect_test.py Traceback (most recent call last): File "object_detection/detect_test.py", line 81, in <module> feed_dict={image_tensor: image_np_expanded}) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 789, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python

问题 I am super new to the field of object detection. I was wondering if anyone can help me somehow on how I can download and use the object detection datasets such as coco or pascal. When I go to their website even after downloading the datasets i feel like i dont know what should i do with them... I know this question is stupid, but a hint to start can be super useful. Thanks 回答1: I'm using: python 3.5 on Ubuntu 16.04 Firstly, there are three things you'd want to download and unzip: 1) Cocoapi -

问题 I'd like to ask a general question about DNN based object detection algorithms such as Yolo, SSD or R-CNN. Assume I'd like to detect mobile phones on small images, where - consequently - the mobile devices themselves are super small, moreover, it's nearly impossible to detect them by only looking at those pixels which they appear on. For instance, looking at a 300x300 image, the mobile shows up on a 7x5 grid, so only by looking at the 7x5 picture no one can surely decide what can be seen