Data Augmentation output size

If there is one training image then will the network be trained on one training image which is modified by TLT or be trained on two training images , one original, one from augmentation ? Or will there be one original and two from augmentation ? If it’s trained only on one image , which augmentation was done - I have listed the augmentation I used below?

Below is my augmentation from the config file:

augmentation_config {
preprocessing {
output_image_width: 840
output_image_height: 480
min_bbox_width: 1.0
min_bbox_height: 1.0
output_image_channel: 3
spatial_augmentation {
hflip_probability: 0.5
zoom_min: 1.0
zoom_max: 1.0
translate_max_x: 8.0
translate_max_y: 8.0
color_augmentation {
hue_rotation_max: 25.0
saturation_shift_max: 0.20000000298
contrast_scale_max: 0.10000000149
contrast_center: 0.5

For your config, preprocessing + spatial augmentation + color augmentation will be applied.
The dataloader will generate matrix which applies all the color and spatial transformations.
Spatial augmentation includes flipping, zooming and translation.
Color augmentation includes color shift, hue_rotation, saturation shift, and contrast adjustment. For your case, you delete the color shift.

Just to clarify, If i have 1300 images in my dataset, it will apply to the augmentation to the 1300 images. Even after augmentation my dataset size will stay 1300 images?

Yes. Each epoch stays 1300 images. But the images will vary for every epochs.