gradio run error

[VisionZQ]

Hi,
1、请问运行gradio脚本中CKPT_PATH=该如何指定，我huggingface中下载模型，并指定路径，设置TRANSFORMERS_OFFLINE=1，运行报错依然需要online下载模型？
2、

我手动指定了路径后，模型load会被block住？

[xk-huang]

Hi!

1. 可以参考这个 issue How could I try your gradio app? #2 。

2. 使用预训练权重的话不用指定模型路径。而 block 的原因可能是无法连接到 huggingface https://zhuanlan.zhihu.com/p/647843635 。

[VisionZQ]

Hi!

1. 可以参考这个 issue how could I try your gradio app? #2 。
2. 使用预训练权重的话不用指定模型路径。而 block 的原因可能是无法连接到 huggingface https://zhuanlan.zhihu.com/p/647843635 。

非常感谢您的回复，我按照你的指导进行了实验，但依然出现一些问题，我离线下载了pretrain模型，并按照说明配置：

但运行依然会在线下载模型，请问还需要下载其他模型吗？vit? 感谢回复！ 报错如下：
`eval_data: []
eval_data_overrides: []
model:
model_max_length: 20
cache_dir: .model.cache
model_name_or_path: ./models/segment-caption-anything-gpt2_large-pt
sam_model_name_or_path: facebook/sam-vit-huge
lm_head_model_name_or_path: gpt2-large
additional_num_hidden_layers: 2
num_caption_tokens: 1
num_task_tokens: 6
num_caption_heads: 1
data_transforms: null
data_collator:
use_instruction: false
instruction_mapping_json: null

[2024-04-25 10:23:55,352][src.arguments][INFO] - Running on ctmt231220145413fj2-5979b84dbb-v85nv
[2024-04-25 10:23:56,178][src.arguments][WARNING] - Process rank: 0, device: cpu, log_level: 20 n_gpu: 8 distributed training: True, 16-bits training: False, bf16 training: False
[2024-04-25 10:23:56,181][main][INFO] - Try to load sas_key from .env file: False.
/opt/conda/envs/sca-v2/lib/python3.8/site-packages/transformers/processing_utils.py:215: FutureWarning: The use_auth_token argument is deprecated and will be removed in v5 of Transformers. Please use token instead.
warnings.warn(
pretrained_model_name_or_path = facebook/sam-vit-huge
path_or_repo_id = facebook/sam-vit-huge
Error executing job with overrides: ['+model=base_sca_multitask_v2', 'model.model_name_or_path=./models/segment-caption-anything-gpt2_large-pt', 'model.lm_head_model_name_or_path=gpt2-large']
Traceback (most recent call last):
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connection.py", line 174, in _new_conn
conn = connection.create_connection(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/util/connection.py", line 95, in create_connection
raise err
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/util/connection.py", line 85, in create_connection
sock.connect(sa)
socket.timeout: timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connectionpool.py", line 715, in urlopen
httplib_response = self._make_request(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connectionpool.py", line 404, in _make_request
self._validate_conn(conn)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connectionpool.py", line 1058, in _validate_conn
conn.connect()
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connection.py", line 363, in connect
self.sock = conn = self._new_conn()
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connection.py", line 179, in _new_conn
raise ConnectTimeoutError(
urllib3.exceptions.ConnectTimeoutError: (<urllib3.connection.HTTPSConnection object at 0x7f1c80a3ed90>, 'Connection to huggingface.co timed out. (connect timeout=10)')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/requests/adapters.py", line 489, in send
resp = conn.urlopen(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/connectionpool.py", line 799, in urlopen
retries = retries.increment(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/urllib3/util/retry.py", line 592, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /facebook/sam-vit-huge/resolve/main/preprocessor_config.json (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7f1c80a3ed90>, 'Connection to huggingface.co timed out. (connect timeout=10)'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/file_download.py", line 1238, in hf_hub_download
metadata = get_hf_file_metadata(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/utils/_validators.py", line 118, in _inner_fn
return fn(*args, **kwargs)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/file_download.py", line 1631, in get_hf_file_metadata
r = _request_wrapper(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/file_download.py", line 385, in _request_wrapper
response = _request_wrapper(
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/file_download.py", line 408, in _request_wrapper
response = get_session().request(method=method, url=url, **params)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/requests/sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/requests/sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/huggingface_hub/utils/_http.py", line 67, in send
return super().send(request, *args, **kwargs)
File "/opt/conda/envs/sca-v2/lib/python3.8/site-packages/requests/adapters.py", line 553, in send
raise ConnectTimeout(e, request=request)
requests.exceptions.ConnectTimeout: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /facebook/sam-vit-huge/resolve/main/preprocessor_config.json (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x7f1c80a3ed90>, 'Connection to huggingface.co timed out. (connect timeout=10)'))"), '(Request ID: 15027d7a-e2da-467e-a939-ae5ee524d022)')

The above exception was the direct cause of the following exception:`

[xk-huang]

我这边使用 docker 环境无法复现你的报错，可以尝试用 docker 配置环境。

另外从上面的报错日志看，应该是下载 sam vit huge 超时导致问题：

Max retries exceeded with url: /facebook/sam-vit-huge/resolve/main/preprocessor_config.json 

如果 docker 也不行，则可以手动下载模型：
把 config 中的：

sam_model_name_or_path: facebook/sam-vit-huge
lm_head_model_name_or_path: gpt2-large

替换为：

sam_model_name_or_path: ./models/facebook/sam-vit-huge
lm_head_model_name_or_path: ./models/gpt2-large

[VisionZQ]

我这边使用 docker 环境无法复现你的报错，可以尝试用 docker 配置环境。

另外从上面的报错日志看，应该是下载 sam vit huge 超时导致问题：

Max retries exceeded with url: /facebook/sam-vit-huge/resolve/main/preprocessor_config.json 

如果 docker 也不行，则可以手动下载模型： 把 config 中的：

sam_model_name_or_path: facebook/sam-vit-huge
lm_head_model_name_or_path: gpt2-large

替换为：

sam_model_name_or_path: ./models/facebook/sam-vit-huge
lm_head_model_name_or_path: ./models/gpt2-large

非常感谢你耐心的指导。。最后发现从hugging face下载示例图片block了。现在可以运行了，Nice。。