README update for DELF training with autoencoder (#9607)

* Merged commit includes the following changes:
326369548  by Andre Araujo:

    Fix import issues.

--
326159826  by Andre Araujo:

    Changed the implementation of the cosine weights from Keras layer to tf.Variable to manually control for L2 normalization.

--
326139082  by Andre Araujo:

    Support local feature matching using ratio test.

    To allow for easily choosing which matching type to use, we rename a flag/argument and modify all related files to avoid breakages.

    Also include a small change when computing nearest neighbors for geometric matching, to parallelize computation, which saves a little bit of time during execution (argument "n_jobs=-1").

--
326119848  by Andre Araujo:

    Option to measure DELG latency taking binarization into account.

--
324316608  by Andre Araujo:

    DELG global features training.

--
323693131  by Andre Araujo:

    PY3 conversion for delf public lib.

--
321046157  by Andre Araujo:

    Purely Google refactor

--

PiperOrigin-RevId: 326369548

* Added export of delg_model module.

* README update to explain training DELG global features head

* Added guidelines for DELF hyperparameter values

* Fixed typo

* Added mention about remaining training flags.

* Merged commit includes the following changes:
334723489  by Andre Araujo:

    Backpropagate global and attention layers together.

--
334228310  by Andre Araujo:

    Enable scaling of local feature locations to the resized resolution.

--

PiperOrigin-RevId: 334723489

* Merged commit includes the following changes:
347032253  by Andre Araujo:

    Updated local and global_and_local model export scripts for exporting models trained with the autoencoder layer.

--
344312455  by Andre Araujo:

    Implement autoencoder in training pipeline.

--
341116593  by Andre Araujo:

    Reduce the default save_interval, to get more frequent checkpoints.

--
341111808  by Andre Araujo:

    Allow checkpoint restoration in DELF training, to enable resuming of training jobs.

--
340138315  by Andre Araujo:

    DELF training script: make it always save the last checkpoint.

--
338731551  by Andre Araujo:

    Add image_size flag in DELF/G OSS training script.

--
338684879  by Andre Araujo:

    Clean up summaries in DELF/G training script.

    - Previously, the call to tf.summary.record_if() was not working, which led to summaries being recorded at every step, leading to too large events files. This is fixed.
    - Previously, some summaries were computed at iteration k, while others at iteration k+1. Now, we standardize summary computations to always run after backpropagation (which means that summaries are reported for step k+1, referring to the batch k).
    - Added a new summary: number of global steps per second; useful to see how fast training is making progress.

    Also a few other small modifications are included:
    - Improved description of the train.py script.
    - Some small automatic reformattings.

--

PiperOrigin-RevId: 347032253

* Updated README for training with autoencoder

* DELF README update after first review.
Co-authored-by: Andre Araujo <andrearaujo@google.com>

research/delf/delf/python/training/README.md

@@ -158,6 +158,9 @@ python3 train.py \
   --logdir=gldv2_training/
 ```
 
+*NOTE: The `--use_autoencoder` parameter is set by default to `True`, therefore
+the model will be by default trained with the autoencoder.*
+
 ### Training with Local and Global Features
 
 It is also possible to train the model with an improved global features head as
@@ -175,6 +178,9 @@ python3 train.py \
   --delg_global_features
 ```
 
+*NOTE: The `--use_autoencoder` parameter is set by default to `True`, therefore
+the model will be by default trained with the autoencoder.*
+
 ### Hyperparameter Guidelines
 
 In order to improve the convergence of the training, the following
@@ -184,9 +190,6 @@ values**:
 * 8 Tesla P100 GPUs: `--batch_size=256`, `--initial_lr=0.01`
 * 4 Tesla P100 GPUs: `--batch_size=128`, `--initial_lr=0.005`
 
-*NOTE*: We are currently working on adding the autoencoder described in the DELG
-paper to this codebase. Currently, it is not yet implemented here. Stay tuned!
-
 ## Exporting the Trained Model
 
 Assuming the training output, the TensorFlow checkpoint, is in the
@@ -200,8 +203,7 @@ model.
 ```
 python3 model/export_local_model.py \
   --ckpt_path=gldv2_training/delf_weights \
-  --export_path=gldv2_model_local \
-  --block3_strides
+  --export_path=gldv2_model_local
 ```
 
 ### DELG global feature-only model
@@ -225,8 +227,7 @@ global features.
 python3 model/export_local_and_global_model.py \
   --ckpt_path=gldv2_training/delf_weights \
   --export_path=gldv2_model_local_and_global \
-  --delg_global_features \
-  --block3_strides
+  --delg_global_features
 ```
 
 ### Kaggle-compatible global feature model