Tudohuang
/

ITT-Image_to_text

Image-Text-to-Text

Model card Files Files and versions

ITT-Image_to_text

146 MB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

This model has 1 file scanned as suspicious.

Tudohuang's picture

Update README.md

d9eaa04 verified almost 2 years ago

.gitattributes

1.52 kB
initial commit almost 2 years ago
README.md

94 Bytes
Update README.md almost 2 years ago
app.py

6.29 kB
Upload 3 files almost 2 years ago
im2text_model_full.pt
Detected Pickle imports (20)
- "torch.nn.modules.batchnorm.BatchNorm2d",
- "__main__.im2text_model",
- "torch._utils._rebuild_tensor_v2",
- "torch.nn.modules.container.Sequential",
- "__main__.RNNDecoder",
- "torch.nn.modules.sparse.Embedding",
- "torch.nn.modules.pooling.AdaptiveAvgPool2d",
- "torch.nn.modules.normalization.GroupNorm",
- "__builtin__.set",
- "collections.OrderedDict",
- "torch.nn.modules.conv.Conv2d",
- "torch.nn.modules.pooling.MaxPool2d",
- "torchvision.models.resnet.Bottleneck",
- "__main__.CNNEncoder",
- "torch.nn.modules.activation.ReLU",
- "torch.nn.modules.rnn.LSTM",
- "torch.FloatStorage",
- "torch._utils._rebuild_parameter",
- "torch.LongStorage",
- "torch.nn.modules.linear.Linear"
How to fix it?
145 MB
xet

Upload 3 files almost 2 years ago
vocab_full.json

496 kB
Upload 3 files almost 2 years ago