GithubHelp home page GithubHelp logo

Comments (22)

ericdoerheit avatar ericdoerheit commented on July 28, 2024 2

Have you used a pre-trained network or where you training from scratch? In the original paper it is described, that they train the first CNN layers for solving a classification task, e. g. based on the ImageNet dataset and then add some more layers and fine-tune for object detection. [Section 2.2, https://arxiv.org/abs/1506.02640] I am not sure whether this is the reason for the problem, but maybe you could try to train with pre-trained weights?

from yolo_tensorflow.

shadowdyj avatar shadowdyj commented on July 28, 2024 1

I have the problem when I train the model without pre-training. The total loss goes from 42 to 10, and cannot get less any more. However I get loss about 6 when I fine-turn the model using the Yolo_small.ckpt .
Is it impossible to train the model without any pre-trained weight?

from yolo_tensorflow.

zy486at189cn avatar zy486at189cn commented on July 28, 2024 1

edit config.py,just as this:

#WEIGHTS_FILE = None
WEIGHTS_FILE = os.path.join(DATA_PATH, 'weights', 'YOLO_small.ckpt')

when turn on the pre-training weights YOLO_small.ckpt,the trained model can make effect!

my test.py which use the trained model ,just like this:

class Detector(object):

def __init__(self, net, weight_file):
    self.net = net
    self.weights_file = weight_file

    self.classes = cfg.CLASSES
    self.num_class = len(self.classes)
    self.image_size = cfg.IMAGE_SIZE
    self.cell_size = cfg.CELL_SIZE
    self.boxes_per_cell = cfg.BOXES_PER_CELL
    self.threshold = cfg.THRESHOLD
    self.iou_threshold = cfg.IOU_THRESHOLD
    self.boundary1 = self.cell_size * self.cell_size * self.num_class
    self.boundary2 = self.boundary1 + self.cell_size * self.cell_size * self.boxes_per_cell

    self.sess = tf.Session()
    self.sess.run(tf.global_variables_initializer())
         
    PATH = **'/media/stockerc/f/wz/project/yolo/data/pascal_voc/output/2018_02_23_11_13'
    print 'Restoring weights from: ' + PATH
    self.saver = tf.train.Saver()
    ckpt = tf.train.get_checkpoint_state(PATH)
    self.saver.restore(self.sess, ckpt.model_checkpoint_path)

from yolo_tensorflow.

joashchn avatar joashchn commented on July 28, 2024

@ailias
i have the seem question ,i changed the input data code(only train 'car' and 'cat'),but after the trainning,nothing can be detected
i did not use any pre-trained weights, and here i have another question,if the class i want to train is not in the pre-trained weights,can i use the pre-train weights?

from yolo_tensorflow.

jongsukchoi avatar jongsukchoi commented on July 28, 2024

@joashchn
hi joashchn
i have same problem with you.
did you solve the this problem?
my goal is the just one object detection in image.
perhaps, your goal is the two object detection in image.

from yolo_tensorflow.

liuhyCV avatar liuhyCV commented on July 28, 2024

@joashchn @ailias did you solve the problem? I have train it and test nothing in cat.jpg or person.jpg. Its training problem?

from yolo_tensorflow.

feitiandemiaomi avatar feitiandemiaomi commented on July 28, 2024

@liuhyCV Did you meet the question of testing noting in person.jpg ? Just like the original jpg ,did not have any output and circle , did you solve the problem?

from yolo_tensorflow.

linydf avatar linydf commented on July 28, 2024

I also meet the same question. I train the download model-YOLO-small ,but finally,I find the result is pretty worse,i set the iteration time is thirty thousands.

from yolo_tensorflow.

ss199302 avatar ss199302 commented on July 28, 2024

Has anyone solved the problem of training?

from yolo_tensorflow.

Liu-Yicheng avatar Liu-Yicheng commented on July 28, 2024

I have the same problems with you. I thought the weight that I trained without pre-training was not good that cause the problem(detect nothing).Then I changed the parameter‘THRESHOLD ’(in the config file) to 0.01,it did work!Although the result was not right!So my conclusion is if our loss can arrive about 6,the weight can be good enough to detect !

from yolo_tensorflow.

ss199302 avatar ss199302 commented on July 28, 2024

@ailias Have you solved the problem of training?

from yolo_tensorflow.

linydf avatar linydf commented on July 28, 2024

now my loss arrive 3. but I am failed to result this condition

from yolo_tensorflow.

ss199302 avatar ss199302 commented on July 28, 2024

@linydf What data set do you use?thanks!

from yolo_tensorflow.

xiaoshuguo750 avatar xiaoshuguo750 commented on July 28, 2024

@joashchn @jongsukchoi
Hi!
How can I changed the code if I want to input data (only train 'car' and 'cat')?
Thank you!
Shu Guo

from yolo_tensorflow.

leadcain84 avatar leadcain84 commented on July 28, 2024

How do you get the 'YOLO_small.ckpt you gave'?
is it your training results? or others.

from yolo_tensorflow.

zy486at189cn avatar zy486at189cn commented on July 28, 2024

from yolo_tensorflow.

MindyZLM avatar MindyZLM commented on July 28, 2024

@joashchn i have same problem with you.
did you solve the this problem?

from yolo_tensorflow.

XiangqianMa avatar XiangqianMa commented on July 28, 2024

My model can get the loss of 3, but it can not detect any right objects. Before i trained this model to fine-tune my own data, i have tried to fine-tune this model on pascal-voc, it can detect the right objects, but it's confidence was very low, such as 0.6.

from yolo_tensorflow.

M000M avatar M000M commented on July 28, 2024

I have the same problem. I doubt that the model is right, but there's some errors in the loss function.

from yolo_tensorflow.

guker avatar guker commented on July 28, 2024

I have the same problem, do you solve it?

from yolo_tensorflow.

guker avatar guker commented on July 28, 2024

Have you used a pre-trained network or where you training from scratch? In the original paper it is described, that they train the first CNN layers for solving a classification task, e. g. based on the ImageNet dataset and then add some more layers and fine-tune for object detection. [Section 2.2, https://arxiv.org/abs/1506.02640] I am not sure whether this is the reason for the problem, but maybe you could try to train with pre-trained weights?

yes, you must pretrain,not train from scrath,otherwise,loss is about 10.0 and does not decrease

from yolo_tensorflow.

LinzzMichael avatar LinzzMichael commented on July 28, 2024

Have you used a pre-trained network or where you training from scratch? In the original paper it is described, that they train the first CNN layers for solving a classification task, e. g. based on the ImageNet dataset and then add some more layers and fine-tune for object detection. [Section 2.2, https://arxiv.org/abs/1506.02640] I am not sure whether this is the reason for the problem, but maybe you could try to train with pre-trained weights?

yes, you must pretrain,not train from scrath,otherwise,loss is about 10.0 and does not decrease

@guker I have some problem,if my the num of detect classes is 5 not 20,how can I pre train,can I pre train with the YOLO_small.ckpt,or I need to pre train with only 5 classes?

from yolo_tensorflow.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.