pytorch1.0 batch of training the neural network
Import Torch Import torch.utils.data the Data AS # provided Torch of a tool to help organize the data structure, called DataLoader, use it to package their data, batch training. torch.manual_seed (1) # reproducible # Batch the number of training data BATCH_SIZE =. 5 BATCH_SIZE =. 8 X = torch.linspace (. 1, 10, 10) # the this iS X data (Torch Tensor) Y = torch.linspace (10,. 1, 10) # the this iS Y data ( Tensor torch) # DataLoader packaging developer tools used to torch their own data. # own (numpy array or other) data format loaded into Tensor, and then put the wrapper. # benefits of using DataLoader is they help you to effectively iterative data # first converted into torch can recognize Dataset = Data.TensorDataset torch_dataset (X, Y) # torch_dataset = Data.TensorDataset (data_tensor = X, Y = target_tensor) # the dataset into DataLoader Loader = Data.DataLoader ( dataset = torch_dataset, # Torch TensorDataset the format the batch_size = BATCH_SIZE, # BATCH size Mini shuffle = True, # random shuffle for Training # random data upset - upset the better num_workers = 2, # subprocesses for loading the data # multithreading to read data ) DEF show_batch (): for Epoch in the Range (3 ): #train entire dataset 3 times # train all / the whole data three times for the STEP, (batch_x, batch_y) in the enumerate (loader): # for the each Training every step of the STEP # loader release a small number of data used to learn the # Train your the Data .. # this is assumed training block ... Print ( ' Epoch: ' , Epoch, ' | the Step: ' , STEP, ' | BATCH X: ' , batch_x.numpy (), ' | Y BATCH: ' , batch_y .numpy ()) IF the __name__ == ' __main__ ' : show_batch ()
# BATCH_SIZE = 5
'''
Epoch: 0 | Step: 0 | batch x: [ 5. 7. 10. 3. 4.] | batch y: [6. 4. 1. 8. 7.]
Epoch: 0 | Step: 1 | batch x: [2. 1. 8. 9. 6.] | batch y: [ 9. 10. 3. 2. 5.]
Epoch: 1 | Step: 0 | batch x: [ 4. 6. 7. 10. 8.] | batch y: [7. 5. 4. 1. 3.]
Epoch: 1 | Step: 1 | batch x: [5. 3. 2. 1. 9.] | batch y: [ 6. 8. 9. 10. 2.]
Epoch: 2 | Step: 0 | batch x: [ 4. 2. 5. 6. 10.] | batch y: [7. 9. 6. 5. 1.]
Epoch: 2 | Step: 1 | batch x: [3. 9. 1. 8. 7.] | batch y: [ 8. 2. 10. 3. 4.]
'''
# BATCH_SIZE = 8
'''
Epoch: 0 | Step: 0 | batch x: [ 5. 7. 10. 3. 4. 2. 1. 8.] | batch y: [ 6. 4. 1. 8. 7. 9. 10. 3.]
Epoch: 0 | Step: 1 | batch x: [9. 6.] | batch y: [2. 5.]
Epoch: 1 | Step: 0 | batch x: [ 4. 6. 7. 10. 8. 5. 3. 2.] | batch y: [7. 5. 4. 1. 3. 6. 8. 9.]
Epoch: 1 | Step: 1 | batch x: [1. 9.] | batch y: [10. 2.]
Epoch: 2 | Step: 0 | batch x: [ 4. 2. 5. 6. 10. 3. 9. 1.] | batch y: [ 7. 9. 6. 5. 1. 8. 2. 10.]
Epoch: 2 | Step: 1 | batch x: [8. 7.] | batch y: [3. 4.]
'''