Skip to content

Dev angela data preprocessing#1

Open
sansangela wants to merge 8 commits intomainfrom
dev_angela_data_preprocessing
Open

Dev angela data preprocessing#1
sansangela wants to merge 8 commits intomainfrom
dev_angela_data_preprocessing

Conversation

@sansangela
Copy link
Owner

No description provided.

@sansangela sansangela requested a review from yuanxuns January 19, 2024 02:36

```bash
pip3 install -r third_party/requirements.txt
python3 social_lstm/main.py
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

改成bazel command

)
dataloader.reset_frame_ptr()

with tf.device(device):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: tf2还需要specify device吗?

train(args)


def train(args):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

把train放到单独一个file

/bazel-*
/bazel_tutorial
*.bazel
*.lock No newline at end of file
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

clang: add end of line

py_binary(
name = "main",
srcs = ["main.py"],
) No newline at end of file
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

clang: add end of line

continue
y_true_dense_representation[sequence_idx, indices, :] = y_true[sequence_idx][:, 1:3]

return -tf.math.reduce_mean(y_true_dense_representation-y_pred) No newline at end of file
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

clang: add end of line

with tf.GradientTape() as tape:
# Forward pass
out = model(dense_representation_tf, lstm_hidden, lstm_cell)
loss = mse_loss(target, out, ped_id_to_index_map) # TODO, placeholder
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: paper里的log likelyhood loss还没implement是吧?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants