object-detection-api

Plot validation loss in Tensorflow Object Detection API

做~自己de王妃 提交于 2021-02-08 03:27:47
问题 I'm using Tensorflow Object Detection API for detection and localization of one class object in images. For these purposes I use pre-trained faster_rcnn_resnet50_coco_2018_01_28 model. I want to detect under/overfitting after training of the model. I see training loss, but after evaluating Tensorboard only shows mAP and Precision metrics and no loss. Is this possible to plot a validation loss on Tensorboard too? 回答1: There is validation loss. Assuming you're using the latest API, the curve

Plot validation loss in Tensorflow Object Detection API

江枫思渺然 提交于 2021-02-08 03:27:02
问题 I'm using Tensorflow Object Detection API for detection and localization of one class object in images. For these purposes I use pre-trained faster_rcnn_resnet50_coco_2018_01_28 model. I want to detect under/overfitting after training of the model. I see training loss, but after evaluating Tensorboard only shows mAP and Precision metrics and no loss. Is this possible to plot a validation loss on Tensorboard too? 回答1: There is validation loss. Assuming you're using the latest API, the curve

Plot validation loss in Tensorflow Object Detection API

删除回忆录丶 提交于 2021-02-08 03:26:27
问题 I'm using Tensorflow Object Detection API for detection and localization of one class object in images. For these purposes I use pre-trained faster_rcnn_resnet50_coco_2018_01_28 model. I want to detect under/overfitting after training of the model. I see training loss, but after evaluating Tensorboard only shows mAP and Precision metrics and no loss. Is this possible to plot a validation loss on Tensorboard too? 回答1: There is validation loss. Assuming you're using the latest API, the curve

Output score/probability for all class for each object with Tensorflow object detection API

亡梦爱人 提交于 2021-01-29 13:27:10
问题 in Tensorflow object detection API, we usually do this for each test image: output_dict = sess.run(tensor_dict, feed_dict={image_tensor: image_np_expanded}) # pdb.set_trace() # all outputs are float32 numpy arrays, so convert types as appropriate output_dict['num_detections'] = int(output_dict['num_detections'][0]) output_dict['detection_classes'] = output_dict['detection_classes'][0].astype(np.int64) output_dict['detection_boxes'] = output_dict['detection_boxes'][0] output_dict['detection

Tensorflow object detection API tutorial error

安稳与你 提交于 2021-01-28 11:48:49
问题 After struggling with compatibility issues between Tensorflow 2.00 and the object detection API, I downgraded to Tensorflow 1.15 to be able to train my own model. after completing the training I modified the jupyter notebook included in the Tensorflow object detection API repo to test on my own images but I keep getting this error: Traceback (most recent call last): File "object_detection_tutorial_converted.py", line 254, in <module> show_inference(detection_model, image_path) File "object

Disable augmentation in tensorflow training pipeline

怎甘沉沦 提交于 2021-01-27 21:01:38
问题 I googled around a bit but I only found questions about enabling data augmentation. I followed this tutorial but with my own dataset (only one class). I already performed data augmentation on my dataset so I deleted the responsible lines from the pipeline.config. Now my pipeline looks like this model { ssd { num_classes: 1 image_resizer { fixed_shape_resizer { height: 640 width: 640 } } feature_extractor { type: "ssd_resnet50_v1_fpn_keras" depth_multiplier: 1.0 min_depth: 16 conv_hyperparams

Determining max batch size with TensorFlow Object Detection API

孤街浪徒 提交于 2021-01-27 19:54:46
问题 TF Object Detection API grabs all GPU memory by default, so it's difficult to tell how much I can further increase my batch size. Typically I just continue to increase it until I get a CUDA OOM error. PyTorch on the other hand doesn't grab all GPU memory by default, so it's easy to see what percentage I have left to work with, without all the trial and error. Is there a better way to determine batch size with the TF Object Detection API that I'm missing? Something like an allow-growth flag

Keras failed to load SavedModel: TypeError 'module' object is not callable

試著忘記壹切 提交于 2021-01-07 01:19:50
问题 I trained an SSD MobileNet v2 network using the TensorFlow Object Detection API with TensorFlow 2 and then converted the trained model into a SavedModel. Now I need to convert the SavedModel to a FrozenGraph in order to make the model compatible with external libraries like OpenCV. I use this example for conversion and I cannot even load the Keras model. from keras.models import load_model model = load_model("training/model/saved_model") Calling load_model() produces an exception: Exception

Keras failed to load SavedModel: TypeError 'module' object is not callable

喜夏-厌秋 提交于 2021-01-07 01:19:05
问题 I trained an SSD MobileNet v2 network using the TensorFlow Object Detection API with TensorFlow 2 and then converted the trained model into a SavedModel. Now I need to convert the SavedModel to a FrozenGraph in order to make the model compatible with external libraries like OpenCV. I use this example for conversion and I cannot even load the Keras model. from keras.models import load_model model = load_model("training/model/saved_model") Calling load_model() produces an exception: Exception

Keras failed to load SavedModel: TypeError 'module' object is not callable

五迷三道 提交于 2021-01-07 01:17:26
问题 I trained an SSD MobileNet v2 network using the TensorFlow Object Detection API with TensorFlow 2 and then converted the trained model into a SavedModel. Now I need to convert the SavedModel to a FrozenGraph in order to make the model compatible with external libraries like OpenCV. I use this example for conversion and I cannot even load the Keras model. from keras.models import load_model model = load_model("training/model/saved_model") Calling load_model() produces an exception: Exception