upload exercises

exercises/exerciseC/process_images.py

@@ -0,0 +1,72 @@
+import os
+import sys
+from multiprocessing import Pool as ProcessPool
+import time
+
+def process_image(input_tuple):
+
+    fname, A = input_tuple
+    n_threads = os.getenv('OMP_NUM_THREADS', '(unset)')
+    print(f"Worker {fname=} OMP_NUM_THREADS={n_threads}", flush=True)
+
+    # Decompose image
+    U, S, Vh = np.linalg.svd(A)
+
+    # Remove first singular value
+    S[0] = 0
+    smat = np.zeros(A.shape, dtype=complex)
+    smat[:min(A.shape), :min(A.shape)] = np.diag(S)
+
+    # Re-compose image
+    A = np.dot(U, np.dot(smat, Vh)).real
+    A = (256*(A - A.min())/A.max()).astype('uint8')
+
+    return A
+    
+
+if __name__ == '__main__':
+    n_processes = int(sys.argv[1])
+    n_threads = int(sys.argv[2])
+    fnames = sys.argv[3:]
+
+    # Check that the output folders exist, or create them if needed
+    if not os.path.isdir('timings'): os.mkdir('timings')
+    if not os.path.isdir('processed_images'): os.mkdir('processed_images')
+
+    print(f"Controller with {n_processes} processes and {n_threads} threads / worker", flush=True)
+
+    # The environment that is set in the parent is inherited by child workers,
+    # we need to set the variable before numpy is imported!
+    os.environ['OMP_NUM_THREADS'] = str(n_threads)
+
+    # We delay the import of numpy because we have to set OMP_NUM_THREADS before import.
+    # We delay the import of PIL in case it uses numpy internally.
+    import numpy as np
+    from PIL import Image
+
+    # I/O Load the images
+    image_arrays = []
+    for fname in fnames:
+        im = Image.open(fname)
+        A = np.array(im)
+        image_arrays.append((fname, A))
+
+    # Time the execution of the pool map
+    start_time = time.time()
+    with ProcessPool(n_processes) as p:
+        new_images = p.map(process_image, image_arrays)
+    elapsed_time = time.time() - start_time
+
+    # I/O save the processed images
+    for im, fname in zip(new_images, fnames):
+        im = Image.fromarray(im)
+        im.save(fname.replace('images', 'processed_images'))
+
+    print(f'{n_processes} processes and {n_threads} threads and {len(fnames)} jobs: {elapsed_time}\n',
+          flush=True)
+
+    # I/O: Save the timing to a unique txt file
+    filename = f'timings/{n_processes:02}_processes_{n_threads:02}_threads.txt'
+    with open(filename, 'w') as file:
+        file.write(f'{n_processes} {n_threads} {elapsed_time:.6f}')
+