Timeline for What is the difference between features in vgg
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 24, 2021 at 4:19 | comment | added | user5520049 | Thanks a lot if you have a good background in captioning can you please give me your email . Thanks in advance | |
| Sep 23, 2021 at 5:26 | vote | accept | user5520049 | ||
| Sep 23, 2021 at 5:25 | comment | added | Nandhu Kishore |
Yes correct, make sure it removed all the fully connected layers using model.summary() before and after applying -2. Then sometimes -2 will remove any Average pooling layer as well, if so please add that layer at the end like. new_layer = tf.keras.layers.GlobalAveragePooling2D()(densenet_model.layers[-1].output). customized_denset = Model(densenet_model.input, new_layer)
|
|
| Sep 23, 2021 at 5:03 | comment | added | user5520049 |
Thakns. you mean like that model=Model(inputs=model.inputs,outputs=model.layers[-2].output)
|
|
| Sep 23, 2021 at 4:53 | comment | added | Nandhu Kishore | sorry to say. last layer is just the classification layer(i mean output layer) in the pre- trained models followed by some fully connected layers, Irrespective of final output, either captioning or normal classification etc you only need the features so it is good to remove the fully connected layers as well. | |
| Sep 23, 2021 at 0:15 | comment | added | user5520049 | Thanks a lot for replying , but excuse me if I want these features for captioning .. will I remove the last only ? | |
| S Sep 22, 2021 at 23:21 | review | First answers | |||
| Sep 22, 2021 at 23:46 | |||||
| S Sep 22, 2021 at 23:21 | history | answered | Nandhu Kishore | CC BY-SA 4.0 |