Yolo3 on Image-net - conv-neural-network

Yolo version 3 is amazing new Deep learning neural network with pre-trained configuration and weights. However, the maximum classes it has is only 80 class from COCO dataset. There is another much larger dataset of Imagenet with more than 22,000 classes.
Does anyone have trained Yolo3 (on Darknet) using Imagenet? Where can we get the pre-trained configuration and weights?

Related

I make Graph embedding using Gensim Doc2vec and then binary classification with 2 layers deep neural network in keras

after making the graph embedding with Doc2vec, I want to make classification with keras, do I have to make embedding layer and put it as input to neural network or I directly use the embedding and split it into training and testing? also did the embedding layer improves the accuracy of neural network or not

Is there a way to create and train a model without transfer learning using tensorflow object-detection api?

I'm using faster_rcnn_resnet50 to train a model which will detect corrosions in images and I want to train a model from scratch instead of using transfer learning.
I don't know if this right but the reason I want to do this is that the already existing weights (which are trained on COCO) will affect my model trained on corrosion images.
One way I would like to do this is randomize or unfreeze the weights of the feature extractor on the resnet50 and then train the model on my images.
but there's no function or an option in the resnet50 config file to randomize or unfreeze weights.
I've made a new labelmap with a single label and tried it with transfer learning. It's working but I would like to have a model is trained just on my images and the previous weights shouldn't affect my predictions.
This is the first time I'm working with object detection and transfer learning. Will the weights of the pre-trained model on COCO affect my model which is trained on custom images of corrosion? How do you use tensorflow object-detection API without transfer learning?

While implementing yolo in darknet, should we train on image net data set?

I have installed darknet in ubuntu and is now trying to implement object detection using yolo v2 on my custom dataset. In the yolo paper, they have told that they have pretrained the network using image net dataset. So, my question is should we also pretrain the network?
Sorry if I'm blunting.
Can someone reply me?
For most cases, if your dataset has lots of similar feature in the pre-trained weight (e.g. person, car), you should use the pre-trained network such as darknet53.conv.74 or darknet19_448.conv.23.
But you can also train the network without using those pre-trained network (training from scratch), for example by removing the weight from the command :
./darknet detector train data/obj.data yolo-obj.cfg

Use models from Keras Applications without pretrained weights

Keras Applications provide implementations of some of the most popular model architectures with weights pretrained on some of the most popular datasets. These predefined models are very handy for transfer learning of problems which are similar to the datasets the models were trained on.
But what if I have a very different problem and want to completely train the models on the new dataset? How can I use the models in Applications for training from scratch based on my own dataset, if I dont have pretrained weights?
You can assign a None to the weights variable, for instance with the inception V3 architecture.
keras.applications.inception_v3.InceptionV3(include_top=False, weights='None', input_shape=input_shape = (img_width, img_height, 3))
include_top=False will allow you to train the top layer with your custom network.
weights='None' means that we are training without any weights if you want to train using imagenet weight you set it to weights='imagenet'

VGG16 trained on grayscale imagenet

I have found the VGG16 network pre-trained on the (color) imagenet database (as .npy). Is there a VGG16 network pre-trained on a gray-scale version of the imagenet database available?
(The usual 'tricks' for using the 3-channel filters of the conv1.1 layer on the gray 1-channel input are not enough for me. I am looking at incremental improvements of the network performance, so I need to see how the transfer learning behaves when the pre-trained model was 'looking' at gray-scale input).
Thanks!
Yes, there's this one:
https://github.com/DaveRichmond-/grayscale-imagenet
Greyscale imagenet trained model, and also a version of it that's finetuned on X-rays. They showed that Imagenet performance barely drops btw.
#GrimSqueaker gave you the code of this paper : https://openaccess.thecvf.com/content_eccv_2018_workshops/w33/html/Xie_Pre-training_on_Grayscale_ImageNet_Improves_Medical_Image_Classification_ECCVW_2018_paper.html
However, the model trained in it is Inception v3 not VGG16.
You have two options:
Use a colored pre-trained VGG16 model and duplicate one channel to the three channels
Train your VGG16 model on the ImageNet grayscaled dataset.
You may find this link useful:
https://github.com/zzangho/VGG16_grayscale

Resources