def download_and_classify_in_batches(complete_links_list, classifier):
print("Total amount of images to be downloaded and classified: %d" %
len(complete_links_list))
for index in range(0, len(complete_links_list), BATCH_SIZE):
time_start = time.time()
print("Downloading and classifying batch: %d -> %d" %
(index, index + BATCH_SIZE))
links_batch = complete_links_list[index:index + BATCH_SIZE]
tensor_images = ImageDownloader.download_images(
links_batch, NUM_DOWNLOAD_THREADS)
if len(tensor_images) == 0:
print("Skipping classification of empy list")
continue
results = classifier.classify_image_tensors(tensor_images)
results_df = DataHandler.convert_classification_result_to_dataframe(
results)
DataHandler.write_classification_result(results_df,
PARQUET_FILE_OUTPUT_LOCATION)
duration = time.time() - time_start
print("Duration of donwloading and classification for batch: %.2f" %
duration)
