Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ResNet50_tensorflow
Commits
8479cc7c
Commit
8479cc7c
authored
May 29, 2020
by
Pengchong Jin
Committed by
A. Unique TensorFlower
May 29, 2020
Browse files
Update README to include the ResNet checkpoint.
PiperOrigin-RevId: 313794704
parent
204c689b
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
0 deletions
+6
-0
official/vision/detection/README.md
official/vision/detection/README.md
+6
-0
No files found.
official/vision/detection/README.md
View file @
8479cc7c
...
@@ -38,6 +38,12 @@ python3 ~/models/official/vision/detection/main.py \
...
@@ -38,6 +38,12 @@ python3 ~/models/official/vision/detection/main.py \
--params_override
=
"{ type: retinanet, train: { checkpoint: { path:
${
RESNET_CHECKPOINT
?
}
, prefix: resnet50/ }, train_file_pattern:
${
TRAIN_FILE_PATTERN
?
}
}, eval: { val_json_file:
${
VAL_JSON_FILE
?
}
, eval_file_pattern:
${
EVAL_FILE_PATTERN
?
}
} }"
--params_override
=
"{ type: retinanet, train: { checkpoint: { path:
${
RESNET_CHECKPOINT
?
}
, prefix: resnet50/ }, train_file_pattern:
${
TRAIN_FILE_PATTERN
?
}
}, eval: { val_json_file:
${
VAL_JSON_FILE
?
}
, eval_file_pattern:
${
EVAL_FILE_PATTERN
?
}
} }"
```
```
The pre-trained ResNet-50 checkpoint can be found here:
```
gs://cloud-tpu-artifacts/resnet/resnet-nhwc-2018-10-14/model.ckpt-112602
```
### Train a custom RetinaNet using the config file.
### Train a custom RetinaNet using the config file.
First, create a YAML config file, e.g.
*my_retinanet.yaml*
. This file specifies
First, create a YAML config file, e.g.
*my_retinanet.yaml*
. This file specifies
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment