karpathy / neuraltalk2

Efficient Image Captioning code in Torch, runs on GPU
5.49k stars 1.26k forks source link

Who explained for me, plz? #176

Open j2233ack opened 7 years ago

j2233ack commented 7 years ago

Traceback (most recent call last): File "prepro.py", line 34, in from scipy.misc import imread, imresize ImportError: cannot import name imread

j2233ack commented 7 years ago

The new issue: parsed input parameters: { "output_json": "coco/cocotalk.json", "images_root": "coco/images", "input_json": "/home/hsu/Desktop/test.json", "word_count_threshold": 5, "max_length": 16, "output_h5": "coco/cocotalk.h5", "num_test": 33, "num_val": 33 } example processed tokens: Traceback (most recent call last): File "prepro.py", line 240, in main(params) File "prepro.py", line 162, in main prepro_captions(imgs) File "prepro.py", line 43, in prepro_captions txt = str(s).lower().translate(None, string.punctuation).strip().split() UnicodeEncodeError: 'ascii' codec can't encode characters in position 0-9: ordinal not in range(128)