Keras - customize pre-trained model (vgg16, vgg19, resent ,MobileNet)
- or -
Post a project like this$100
- Posted:
- Proposals: 4
- Remote
- #2217624
- Expired
Description
Experience Level: Intermediate
I am using pertained models (vgg16, vgg19, resent ,MobileNet)
I have 2 different dataset with below details ,
1. Dataset1: the data is divided in the folders, each contains the label. for example, Folder1 named cat: contains all cats images… Folder2 name Dog: contains all dog images.
2. Dataset2: all the data are located in one folder, the is .csv file which contain image_name and their lables.
I want the following to be done:
1. read all images
2. predict them using those pertained models (vgg16, vgg19, resent ,MobileNet)
3. save the result of the prediction , for each image , for each model
4. in new variable calculate the commutative prediction value for all (vgg16, vgg19, resent ,MobileNet)
5. The program should support any kind of images (including .pgm and .jpg formate )
6. The program should support gray and RGB images (write a function/class to check the input images and convert them to the format supported by those models if needed)
7. the model should divided into functions for easiest monitoring and modifications if needed
8. write the comment is each line showing the purpose of their use.
9. each dataset will have its own .py file
10. using keras
in the end, I need a session to describe the code for me.
The price is FIXED,, Thank you for cooperation.
I have 2 different dataset with below details ,
1. Dataset1: the data is divided in the folders, each contains the label. for example, Folder1 named cat: contains all cats images… Folder2 name Dog: contains all dog images.
2. Dataset2: all the data are located in one folder, the is .csv file which contain image_name and their lables.
I want the following to be done:
1. read all images
2. predict them using those pertained models (vgg16, vgg19, resent ,MobileNet)
3. save the result of the prediction , for each image , for each model
4. in new variable calculate the commutative prediction value for all (vgg16, vgg19, resent ,MobileNet)
5. The program should support any kind of images (including .pgm and .jpg formate )
6. The program should support gray and RGB images (write a function/class to check the input images and convert them to the format supported by those models if needed)
7. the model should divided into functions for easiest monitoring and modifications if needed
8. write the comment is each line showing the purpose of their use.
9. each dataset will have its own .py file
10. using keras
in the end, I need a session to describe the code for me.
The price is FIXED,, Thank you for cooperation.
Hala M.
0% (0)Projects Completed
-
Freelancers worked with
-
Projects awarded
0%
Last project
12 May 2024
Saudi Arabia
New Proposal
Login to your account and send a proposal now to get this project.
Log inClarification Board Ask a Question
-
There are no clarification messages.
We collect cookies to enable the proper functioning and security of our website, and to enhance your experience. By clicking on 'Accept All Cookies', you consent to the use of these cookies. You can change your 'Cookies Settings' at any time. For more information, please read ourCookie Policy
Cookie Settings
Accept All Cookies