add(docs): Add detailed description and usage of Monkey V4 model to README
Browse files- README.md +41 -0
- v4_data_driven/__init__.py +0 -0
README.md
CHANGED
@@ -1,3 +1,44 @@
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: openrail
|
3 |
---
|
4 |
+
|
5 |
+
# Monkey V4 Data Driven + Attention Readout Model Card
|
6 |
+
|
7 |
+
Neural Encoding model for Macaque V4. The model is a combination of a data driven core and an attention readout layer.
|
8 |
+
|
9 |
+
## Model Details
|
10 |
+
### Model Description
|
11 |
+
|
12 |
+
This model is a combination of a data driven core and an attention readout layer.
|
13 |
+
The data driven core is a convolutional neural network and the attention readout layer is a multihead attention layer with each head trained to predict the firing rates of a neuron in Macaque V4.
|
14 |
+
|
15 |
+
### Model Sources
|
16 |
+
For research purposes, we recommend our `nnvision` Github repository (https://github.com/sinzlab/nnvision), which contains the code for the model defintions and training.
|
17 |
+
|
18 |
+
Repository: https://github.com/sinzlab/nnvision
|
19 |
+
Paper: https://www.biorxiv.org/content/10.1101/2023.05.18.541176v1
|
20 |
+
|
21 |
+
### Intended Use
|
22 |
+
|
23 |
+
The model is intended for research purposes only.
|
24 |
+
|
25 |
+
### Model Use
|
26 |
+
|
27 |
+
The model can be used to predict the firing rates of neurons in Macaque V4 given an image.
|
28 |
+
|
29 |
+
#### nnvision
|
30 |
+
The model can be used in Python with the `nnvision` package.
|
31 |
+
```python
|
32 |
+
import torch
|
33 |
+
from nnvision.models.trained_models.v4_data_driven import v4_multihead_attention_ensemble_model
|
34 |
+
|
35 |
+
input_image = torch.rand(1, 100, 100)
|
36 |
+
firing_rate = v4_multihead_attention_ensemble_model(input_image, data_key="all_sessions")
|
37 |
+
```
|
38 |
+
|
39 |
+
### energy-guided diffusion
|
40 |
+
The model can be used in Python with the `energy-guided-diffusion` package.
|
41 |
+
```python
|
42 |
+
from egg.models import models
|
43 |
+
model = models['data_driven']['train']
|
44 |
+
```
|
v4_data_driven/__init__.py
ADDED
File without changes
|