Laurent Mazare 11c7e7bd67 Some fixes for yolo-v3. (#529) ...

* Some fixes for yolo-v3.

* Use the running stats for inference in the batch-norm layer.

* Get some proper predictions for yolo.

* Avoid the quadratic insertion.

2023-08-20 23:19:15 +01:00

..

activation.rs

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

batch_norm.rs

Some fixes for yolo-v3. (#529)

2023-08-20 23:19:15 +01:00

conv.rs

Add a couple functions required for yolo. (#527)

2023-08-20 17:02:05 +01:00

embedding.rs

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

func.rs

Add a couple functions required for yolo. (#527)

2023-08-20 17:02:05 +01:00

group_norm.rs

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

init.rs

Improve the mnist training example. (#276)

2023-07-29 16:28:22 +01:00

layer_norm.rs

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

lib.rs

Add a couple functions required for yolo. (#527)

2023-08-20 17:02:05 +01:00

linear.rs

Add a simple Module trait and implement it for the various nn layers (#500)

2023-08-18 09:38:22 +01:00

loss.rs

Add the cross-entropy loss. (#287)

2023-07-31 14:26:36 +01:00

ops.rs

Implement group-norm. (#334)

2023-08-07 06:53:05 +01:00

optim.rs

Add the AdamW optimizer. (#307)

2023-08-02 14:03:49 +01:00

var_builder.rs

Move the VarMap to a separate file (#525)

2023-08-20 14:25:07 +01:00

var_map.rs

Move the VarMap to a separate file (#525)

2023-08-20 14:25:07 +01:00