Upload TFSegformerForSemanticSegmentation

README.md

@@ -0,0 +1,67 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: slm-segformer-080823
+  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. -->
+
+# slm-segformer-080823
+
+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: 0.0357
+- Validation Loss: 0.0383
+- Validation Mean Iou: 0.8453
+- Validation Mean Accuracy: 0.9366
+- Validation Overall Accuracy: 0.9869
+- Validation Per Category Iou: [0.98646921 0.70414361]
+- Validation Per Category Accuracy: [0.99072207 0.88237991]
+- Epoch: 9
+
+## 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 | Validation Mean Iou | Validation Mean Accuracy | Validation Overall Accuracy | Validation Per Category Iou | Validation Per Category Accuracy | Epoch |
+|:----------:|:---------------:|:-------------------:|:------------------------:|:---------------------------:|:---------------------------:|:--------------------------------:|:-----:|
+| 0.4798     | 0.1807          | 0.6747              | 0.7770                   | 0.9674                      | [0.96669254 0.38268484]     | [0.98185208 0.57215982]          | 0     |
+| 0.1552     | 0.1046          | 0.7352              | 0.7991                   | 0.9779                      | [0.97745298 0.49298956]     | [0.99154204 0.60674898]          | 1     |
+| 0.0981     | 0.1042          | 0.7744              | 0.9090                   | 0.9779                      | [0.97719564 0.5715319 ]     | [0.98310851 0.8349177 ]          | 2     |
+| 0.0744     | 0.0978          | 0.7876              | 0.9431                   | 0.9784                      | [0.97773288 0.59755377]     | [0.98113179 0.90515736]          | 3     |
+| 0.0611     | 0.0728          | 0.8224              | 0.9456                   | 0.9836                      | [0.98310869 0.66170563]     | [0.98654807 0.90455283]          | 4     |
+| 0.0513     | 0.0531          | 0.8330              | 0.9282                   | 0.9856                      | [0.98518512 0.68084932]     | [0.99000668 0.86647783]          | 5     |
+| 0.0469     | 0.0514          | 0.8326              | 0.9460                   | 0.9850                      | [0.98451475 0.68075519]     | [0.9879771  0.90405278]          | 6     |
+| 0.0413     | 0.0406          | 0.8452              | 0.9360                   | 0.9869                      | [0.9864742  0.70392259]     | [0.99077125 0.88115845]          | 7     |
+| 0.0385     | 0.0412          | 0.8495              | 0.9309                   | 0.9875                      | [0.98715291 0.71182272]     | [0.99186047 0.86989475]          | 8     |
+| 0.0357     | 0.0383          | 0.8453              | 0.9366                   | 0.9869                      | [0.98646921 0.70414361]     | [0.99072207 0.88237991]          | 9     |
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- TensorFlow 2.12.0
+- Tokenizers 0.13.3

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": "boundary"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "background": 0,
+    "boundary": 1
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "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": "4.31.0"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc13923a268ad03d13287bd91e8b897c17cd1c6ae1e0aba371dad6560d072039
+size 15133552