This repository has been archived by the owner on Apr 7, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 2
Weekly Report 13 (07.08. ~ 07.12.)
NXXR edited this page Jul 12, 2019
·
1 revision
- Overview of Workstation Setup
- Summary of Movie Review Classification
- Summary of Newswire Topic Classification
- Downloaded and prepares datasets (originally 25.000 images)
- 2.000 training images (1.000 dogs/cats)
- 1.000 validation images (500 dogs/cats)
- 1.000 testing images (500 dogs/cats)
- Network Model Summary:
| Layer | (type) | Output Shape | Param # |
|---|---|---|---|
| conv2d_1 | Conv2D | (None, 148, 148, 32) | 896 |
| max_pooling2d_1 | MaxPooling2D | (None, 74, 74, 32) | 0 |
| conv2d_2 | Conv2D | (None, 72, 72, 64) | 18496 |
| max_pooling2d_2 | MaxPooling2D | (None, 36, 36, 64) | 0 |
| conv2d_3 | Conv2D | (None, 34, 34, 128) | 73856 |
| max_pooling2d_3 | MaxPooling2D | (None, 17, 17, 128) | 0 |
| conv2d_4 | Conv2D | (None, 15, 15, 128) | 147584 |
| max_pooling2d_4 | MaxPooling2D | (None, 7, 7, 128) | 0 |
| flatten_1 | Flatten | (None, 6272) | 0 |
| dense_1 | Dense | (None, 512) | 3211776 |
| dense_2 | Dense | (None, 1) | 513 |
Total params: 3,453,121 Trainable params: 3,453,121 Non-trainable params: 0
- Next Tutorial Project: (Chapter 5.2) Training a convnet from scratch on a small dataset (p. 130 ff.)