Upload TFSegformerForSemanticSegmentation

README.md

@@ -0,0 +1,73 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: sf_20240219_v1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# sf_20240219_v1
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.0640
+- Validation Loss: 0.0852
+- Epoch: 19
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.3507     | 0.2338          | 0     |
+| 0.1528     | 0.1519          | 1     |
+| 0.1186     | 0.1249          | 2     |
+| 0.1038     | 0.1116          | 3     |
+| 0.1008     | 0.0938          | 4     |
+| 0.0907     | 0.0920          | 5     |
+| 0.0936     | 0.1053          | 6     |
+| 0.0898     | 0.0914          | 7     |
+| 0.0843     | 0.0833          | 8     |
+| 0.0795     | 0.0828          | 9     |
+| 0.0779     | 0.0875          | 10    |
+| 0.0750     | 0.0818          | 11    |
+| 0.0729     | 0.0877          | 12    |
+| 0.0723     | 0.0769          | 13    |
+| 0.0709     | 0.0939          | 14    |
+| 0.0722     | 0.0787          | 15    |
+| 0.0692     | 0.0796          | 16    |
+| 0.0663     | 0.0736          | 17    |
+| 0.0651     | 0.0727          | 18    |
+| 0.0640     | 0.0852          | 19    |
+
+
+### Framework versions
+
+- Transformers 4.37.0
+- TensorFlow 2.15.0
+- Datasets 2.1.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,78 @@
+{
+  "_name_or_path": "nvidia/mit-b0",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "background",
+    "1": "water"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "background": 0,
+    "water": 1
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 6,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c7706374181c9ed31229c27a5741d253dcf764dcc35ff9ac2d560e3ae5f311
+size 15152368