Closed CDLCHOI closed 12 months ago
I simply remove the suffix .gz and open the .txt file, the content is:
version https://git-lfs.github.com/spec/v1 oid sha256:924691ac288e54409236115652ad4aa250f48203de50a9e4722a6ecd48d6804a size 1356917
This repo is uploaded with git-lfs. Maybe you can try
git lfs install & git clone https://github.com/blackgold3/SemanticBoost.git
If it does not work, this file is from
Please replace it with the source file.
Thanks. git lfs does not work , but I get it from the source
I simply run the inference code, python inference.py --prompt "A person walks forward and sits down on the chair." --length "120" --mode ncamd --size 1024 --render "3dslow" -f -e, and encounter the problem Traceback (most recent call last): File "/root/project/SemanticBoost-main/inference.py", line 2, in
from mdm.visual_api import Visualize
from mdm.sample import Predictor as mdm_predictor
File "/root/project/SemanticBoost-main/mdm/sample.py", line 5, in
from mdm.model_util import create_model_and_diffusion, load_model_wo_clip, create_trt_model
File "/root/project/SemanticBoost-main/mdm/model_util.py", line 1, in
from mdm.model.mdm import MDM
File "/root/project/SemanticBoost-main/mdm/model/mdm.py", line 5, in
from mdm.model import clip
File "/root/project/SemanticBoost-main/mdm/model/clip/init.py", line 1, in
from .clip import *
File "/root/project/SemanticBoost-main/mdm/model/clip/clip.py", line 28, in
_tokenizer = _Tokenizer()
File "/root/project/SemanticBoost-main/mdm/model/clip/simple_tokenizer.py", line 66, in init
merges = gzip.open(bpe_path).read().decode("utf-8").split('\n')
File "/opt/conda/envs/boost/lib/python3.9/gzip.py", line 300, in read
return self._buffer.read(size)
File "/opt/conda/envs/boost/lib/python3.9/gzip.py", line 487, in read
if not self._read_gzip_header():
File "/opt/conda/envs/boost/lib/python3.9/gzip.py", line 435, in _read_gzip_header
raise BadGzipFile('Not a gzipped file (%r)' % magic)
gzip.BadGzipFile: Not a gzipped file (b've')
File "/root/project/SemanticBoost-main/mdm/visual_api.py", line 17, in
Is it a problem file? mdm/model/clip/bpe_simple_vocab_16e6.txt.gz