youngyi / 6000b_deeplearning_project2

6000B_project2_transfer

6000B_project2_transfer

6000B_project2_transfer In this project, you are required to train a deep model and then test on a test set including 5 kinds of flowers. Data set is avaiable on Dropbox: data.zip download There are 3 txt files stroring the pathes of training data, validation data and test data respectively. Each line in train.txt and val.txt corresponds to a data sample's path and label, which are splited by a space. The format: You need to train a deep model on the training set. You need to predict the class labels of the test data points whose pathes are stored in test.txt. The prediction of your model on the test dataset should be stored in a txt file. Each line stores the predicted class label for the corresponding test data point in test.txt. The format:$LABEL The file name of the txt file should be project2_student id.

1. Readme file is introduce the server and GPU how to start.
2. the main file is running this project. 3.image file is to analysis the validatain path file. For example, if your student id is 10001, then the txt file should be named 'project2_10001.txt'. You have to submit a 1-2 page report in a pdf file on what model you used and additional operations you made. The file name of the pdf file should be project2_student id_report. For example, if your student id is 10001, then the txt file should be named 'project2_10001_report.pdf'. Grading will be based on the testing accuracy.