We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
2 parents 7074952 + 891dc6c commit 684c503Copy full SHA for 684c503
efficientdet/README.md
@@ -279,6 +279,16 @@ Finetune needs to use --ckpt rather than --backbone_ckpt.
279
--hparams=voc_config.yaml \
280
--use_tpu=False
281
282
+If you want to do inference for custom data, you can run
283
+
284
+ # Setting hparams-flag is needed sometimes.
285
+ !python model_inspect.py --runmode=infer \
286
+ --model_name=efficientdet-d0 --ckpt_path=efficientdet-d0 \
287
+ --hparams=voc_config.yaml \
288
+ --input_image=img.png --output_image_dir=/tmp/
289
290
+You should check more details of runmode which is written in caption-4.
291
292
## 9. Training EfficientDets on TPUs.
293
294
To train this model on Cloud TPU, you will need:
0 commit comments