Failed test case: create_train_val_dirs has incorrect type

[nilosreesengupta]

Hello @KALLOL_ROY ,

There are mistakes in every function. I am explaining you one by one here.

1ST Function: create_train_val_dirs

Details of failed tests for create_train_test_dirs

Hello @Ran_Duan , You’re welcome! Thanks for sending your file.I have reciprocated the same on my end and fixed the issue now. In the first graded function, there has been an error as per the test case, though outputs are fine. It’s mentioned in the hint : # Don't hardcode the paths. Use os.path.join to append the new directories to the root_path parameter You had written code for every directory/path individually.Though output comes the expected, but approach was different from what was r…

2ND Function : split_data

Test your split data function not printing expected output

Hello @Waffles , Thanks for your response! I have seen your code snippet. I will be explaining here in detail and hope this will clear all your doubts. For split function, you have directly written directories without defining anything before like this : TRAINING_DIR = train_dir VALIDATION_DIR = validation_dir For which you were getting 0 images. You need to define the things at first, step by step. I would suggest you to go through the hint . It’s given in the hint : All images should…

3RD Function : train_val_generators

Under : Instantiate the ImageDataGenerator class (don’t forget to set the rescale argument)

1. Rescale should be floating point
2. Batch_size is wrong

4TH Function : create_model

Hint is given:

Complete the create_model function below which should return a Keras’ Sequential model.
Aside from defining the architecture of the model, you should also compile it so make sure to use a loss function that is compatible with the class_mode you defined in the previous exercise, which should also be compatible with the output of your network. You can tell if they aren’t compatible if you get an error during training.
Note that you should use at least 3 convolution layers to achieve the desired performance.

1. Half part is correct, but you have taken too many layers.
2. Optimizer is wrong.
3. And several Parameters are not correct.

I would suggest you to go through the lessons properly.

Hope this helps.

With regards,
Nilosree Sengupta