Updated README

sklearn is now optional

README.md

@@ -8,17 +8,26 @@ the GSPR loss function with a second-order polynomial.
 
 Prerequisite
 ------------
-This program uses the following libraries (other versions might work):
+This program uses the following libraries (tested with the following version):
+* cython 0.29
+* numpy 1.21
+* scipy 1.7.1
+* soundfile 0.9
+* scikit-learn 1.0 (needed if you use the hyper resolution mode)
+* pandas 1.3 (needed only for saving in a non CSV format)
+* tqdm 4.62 (optional if you want a progress bar)
 
 Usage
 -----
-
+```
 usage: gsrp_tdoa_hyperres.py [-h] [-c CHANNELS] [-i INVERSE] [-f FRAME_SIZE]
-                             [-s HOP_SIZE] [-m MAX_TDOA] [-l LOW] [-u UP]
-                             [-d DECIMATE] [-t] [-e] [--start SECONDS]
-                             [--end SECONDS]
+                             [-s STRIDE | -p STRIDE] [-m MAX_TDOA]
+                             [-S SECONDS] [-E SECONDS] [-l LOW] [-u UP]
+                             [-d DECIMATE] [-t] [-e] [-n] [-w]
+                             [-M {prepare,on-the-fly,auto,smart}] [-q QUOTA]
+                             [-v]
                              infile outfile
-
+```
 
 Arguments
 -----
@@ -29,10 +38,9 @@ positional arguments:
   infile                The sound file to process.
   outfile               The text or npy file to write results to. Each row
                         gives the position (in samples), cross-correlation
-                        product, the independent TDOAs (in samples), and TDOAs
-                        derived from the independent ones. For plots, the
-                        panes give the cross-correlation product, independent
-                        TDOAS and derived TDOAs from top to bottom.
+                        product in decibel (normalized and unormalized), the
+                        independent TDOAs (in samples), and TDOAs derived from
+                        the independent ones.
 
 optional arguments:
   -h, --help            show this help message and exit
@@ -51,11 +59,13 @@ Channels:
 Size settings:
   -f FRAME_SIZE, --frame-size FRAME_SIZE
                         The size of the cross-correlation frames in seconds
-                        (default: 0.2)
+                        (default: 0.02)
   -s STRIDE, --stride STRIDE
                         The step between the beginnings of sequential frames
-                        in seconds (default: 0.01), or the postion in second
-                        if csv file path is given.
+                        in seconds (default: 0.01)
+  -p STRIDE, --pos STRIDE
+                        The position in second from csv file path. Not allowed
+                        if stride is set
   -m MAX_TDOA, --max-tdoa MAX_TDOA
                         The maximum TDOA in seconds (default: 0.0011).
   -S SECONDS, --start SECONDS
@@ -76,18 +86,27 @@ Other:
   -e, --erase           Erase existing outfile. If outfile exist and --erase
                         is not provide, the script will exit.
   -n, --no-hyperres     Disable the hyper resolution evalutation of the TDOA
-  -M {smart,auto,on-the-fly,prepare}, --mode {smart,auto,on-the-fly,prepare}
-                        How to explore the TDOA space (default: prepare).
-                        'prepare' precomputes all the possible TDOA
+  -w, --wide            Use only one level to concatenate the normal and
+                        hyperres results. Behaviour depends on the output file
+                        type.
+  -M {prepare,on-the-fly,auto,smart}, --mode {prepare,on-the-fly,auto,smart}
+                        How to explore the TDOA space (default: smart).
+                        prepare precomputes all the possible TDOA
                         pairs and then evaluate them. All the results are save
                         in memory.
-                        'on-the-fly' compute the TDOA pairs at the same
+                        on-the-fly compute the TDOA pairs at the same
                         time as it compute the loss function. Only the maximum
-                        is saved. Can be slower than 'prepare'.
-                        'smart' gradually increase the search space dimension, '
-                        reducing the number of tdoa to evaluate.
-                        'auto' automatically try to pick the right
+                        is saved. Can be slower than prepare.
+                        smart gradually increase the search space
+                        dimension, reducing the number of tdoa to evaluate.
+                        auto automatically try to pick the right
                         method.
-
-Process finished with exit code 0
+  -q QUOTA, --quota QUOTA
+                        Memory limit in bytes for the
+                        {BColors.BOLD}smart{BColors.ENDC} method. If hit, halt
+                        the computation of the current frame and skip to the
+                        next one. Note that it does not account for other
+                        memory usage, such as the sound data. Can be a unit
+                        such as GB, GiO, Ko, ...
+  -v, --verbose         Activate verbose for smart mode
 ```

gsrp_tdoa_hyperres.py

@@ -8,9 +8,6 @@ import scipy.signal as sg
 import soundfile as sf
 from numpy.fft import rfft, irfft
 from scipy.signal.windows import tukey
-from sklearn.linear_model import LinearRegression
-from sklearn.pipeline import Pipeline
-from sklearn.preprocessing import PolynomialFeatures
 
 from gsrp_smart_util import *
 
@@ -104,6 +101,10 @@ def corr(data, pos, w_size, max_tdoa, decimate=1, mode='prepare', hyper=True, ve
     tdoas = np.zeros((len(pos), num_channel_pairs + 2), np.float32)
 
     if hyper:   # prepare hyper res
+        from sklearn.linear_model import LinearRegression
+        from sklearn.pipeline import Pipeline
+        from sklearn.preprocessing import PolynomialFeatures
+
         tdoas2 = np.zeros((len(pos), num_channel_pairs + 2), np.float32)
         poly = PolynomialFeatures(2)
         lin = LinearRegression()