models

models copied to clipboard

Understanding pipeline.config

3

I am trying transfer learning on a pre trained model present in the [TensorFlow 2 Detection Model Zoo](https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md) using my own custom data. I was looking into `pipeline.config` file on...

santhoshnumberone

Looking for a pre-trained model of DCN V2. https://github.com/tensorflow/models/tree/master/official/recommendation/ranking

ashiqimranintel

The order of object detection output tensors in TF2 TFLITE model is different from TF1 and from description in export_tflite_graph_tf2.py

2

# Prerequisites Please answer the following questions for yourself before submitting an issue. [+] I am using the latest TensorFlow Model Garden release and TensorFlow 2. [+] I am reporting...

akotlarsky

Validation loss always equals zero for Instance/Semantic Segmentation with Model Garden

3

My experiments for instance segmentation output `'validation_loss': 0.0`, every time the metrics are summarized. It also happens in the official tutorials of instance/semantic segmentation. I’m running the notebook [Instance Segmentation...

luiz-felipe-moreira

# Prerequisites #the raw data and code # x = np.sin(2 * np.pi * freq * t) #input_batch = vggish_input.waveform_to_examples(x, sr) #my data and code #wavefile audio_path="01.wav" input_batch=vggish_input.wavfile_to_examples(audio_path) #ERROR AssertionError:...

Sarahsus

Parameter server can not run

2

environment: CUDA 1.17 tensorflow2.14 code: https://github.com/tensorflow/models/blob/master/official/recommendation/ncf_keras_main.py command: python3 /LLM/models/official/recommendation/ncf_keras_main.py --distribution_strategy parameter_server --model_dir /LLM/models/dataset/ncf_model --data_dir /LLM/models/dataset/ --dataset ml-1m --train_epochs 3 --batch_size 8000 --learning_rate 0.00382059 --beta1 0.783529 --beta2 0.909003 --epsilon 1.45439e-07 --layers...

xiaobai52HZ

# Prerequisites Please answer the following question for yourself before submitting an issue. - [x] I checked to make sure that this feature has not been requested already. ## 1....

davelista

File "C:\Users\ \.conda\envs\tf_tecent\lib\site-packages\object_detection\utils\label_map_util.py", line 175, in load_labelmap text_format.Merge(label_map_string, label_map) File "C:\Users\ \.conda\envs\tf_tecent\lib\site-packages\google\protobuf\text_format.py", line 719, in Merge return MergeLines( File "C:\Users\ \.conda\envs\tf_tecent\lib\site-packages\google\protobuf\text_format.py", line 793, in MergeLines return parser.MergeLines(lines, message) File "C:\Users\...

kirby7802

fixes #9927: pascal_voc_detection_metrics low scores for first catategory in label_map

2

Only add 1 if there is at least one element greater than 0 per row for ground-truth See also issue #9927 This change should reviewed in detail, maybe this could...

Gabriel-Goldschmitt

Support TFLite and TFJS conversion for CenterNet multi-class keypoints

1

# Description Rewrote the `_postprocess_keypoints_multi_class()` method in `center_net_meta_arch.py` to not use `tf.tensor_scatter_nd_add` ops, which seem to: - Break conversion to TFJS (Error message explicitly says `TensorScatterAdd` is not supported). -...

biantsh