Commit d2200548 authored by Pengchong Jin's avatar Pengchong Jin Committed by A. Unique TensorFlower
Browse files

Update the README.

PiperOrigin-RevId: 313865079
parent afdf2599
...@@ -38,11 +38,16 @@ python3 ~/models/official/vision/detection/main.py \ ...@@ -38,11 +38,16 @@ 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: The pre-trained ResNet-50 checkpoint can be downloaded [here](https://storage.cloud.google.com/cloud-tpu-checkpoints/model-garden-vision/detection/resnet50-2018-02-07.tar.gz).
Note: The ResNet implementation under
[detection/](https://github.com/tensorflow/models/tree/master/official/vision/detection)
is currently different from the one under
[classification/](https://github.com/tensorflow/models/tree/master/official/vision/image_classification),
so the checkpoints are not compatible.
We will unify the implementation soon.
```
https://storage.cloud.google.com/cloud-tpu-checkpoints/model-garden-vision/detection/resnet50-2018-02-07.tar.gz
```
### Train a custom RetinaNet using the config file. ### Train a custom RetinaNet using the config file.
...@@ -150,11 +155,15 @@ python3 ~/models/official/vision/detection/main.py \ ...@@ -150,11 +155,15 @@ python3 ~/models/official/vision/detection/main.py \
--params_override="{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="{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: The pre-trained ResNet-50 checkpoint can be downloaded [here](https://storage.cloud.google.com/cloud-tpu-checkpoints/model-garden-vision/detection/resnet50-2018-02-07.tar.gz).
Note: The ResNet implementation under
[detection/](https://github.com/tensorflow/models/tree/master/official/vision/detection)
is currently different from the one under
[classification/](https://github.com/tensorflow/models/tree/master/official/vision/image_classification),
so the checkpoints are not compatible.
We will unify the implementation soon.
```
https://storage.cloud.google.com/cloud-tpu-checkpoints/model-garden-vision/detection/resnet50-2018-02-07.tar.gz
```
### Train a custom Mask R-CNN using the config file. ### Train a custom Mask R-CNN using the config file.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment