Commit
·
e86180f
1
Parent(s):
4500ac5
Upload semanticallysegmentdeezglaciers.ipynb
Browse files
semanticallysegmentdeezglaciers.ipynb
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"cells": [
|
3 |
{
|
4 |
"cell_type": "code",
|
5 |
-
"execution_count":
|
6 |
"metadata": {
|
7 |
"colab": {
|
8 |
"base_uri": "https://localhost:8080/"
|
@@ -10,24 +10,7 @@
|
|
10 |
"id": "c0C76YvrvDbu",
|
11 |
"outputId": "526c8200-e257-45d7-89ec-6c4d6f30d5d0"
|
12 |
},
|
13 |
-
"outputs": [
|
14 |
-
{
|
15 |
-
"name": "stdout",
|
16 |
-
"output_type": "stream",
|
17 |
-
"text": [
|
18 |
-
"1\n",
|
19 |
-
"2\n",
|
20 |
-
"3\n",
|
21 |
-
"4\n",
|
22 |
-
"5\n",
|
23 |
-
"5.1\n",
|
24 |
-
"5.2\n",
|
25 |
-
"5.3\n",
|
26 |
-
"6\n",
|
27 |
-
"7\n"
|
28 |
-
]
|
29 |
-
}
|
30 |
-
],
|
31 |
"source": [
|
32 |
"import torch\n",
|
33 |
"import matplotlib.pyplot as plt\n",
|
@@ -68,7 +51,7 @@
|
|
68 |
},
|
69 |
{
|
70 |
"cell_type": "code",
|
71 |
-
"execution_count":
|
72 |
"metadata": {
|
73 |
"colab": {
|
74 |
"base_uri": "https://localhost:8080/",
|
@@ -156,43 +139,12 @@
|
|
156 |
"id": "kOiKU_-vvDb1",
|
157 |
"outputId": "531092ef-a3b9-4156-9d9c-a1835feece0a"
|
158 |
},
|
159 |
-
"outputs": [
|
160 |
-
{
|
161 |
-
"name": "stderr",
|
162 |
-
"output_type": "stream",
|
163 |
-
"text": [
|
164 |
-
"Found cached dataset parquet (C:/Users/aashr/.cache/huggingface/datasets/glacierscopessegmentation___parquet/glacierscopessegmentation--secondleg-718284968c2f234c/0.0.0/14a00e99c0d15a23649d0db8944380ac81082d4b021f398733dd84f3a6c569a7)\n"
|
165 |
-
]
|
166 |
-
},
|
167 |
-
{
|
168 |
-
"data": {
|
169 |
-
"application/vnd.jupyter.widget-view+json": {
|
170 |
-
"model_id": "593aa8d59e094d338a2fc5cf0121e1db",
|
171 |
-
"version_major": 2,
|
172 |
-
"version_minor": 0
|
173 |
-
},
|
174 |
-
"text/plain": [
|
175 |
-
" 0%| | 0/1 [00:00<?, ?it/s]"
|
176 |
-
]
|
177 |
-
},
|
178 |
-
"metadata": {},
|
179 |
-
"output_type": "display_data"
|
180 |
-
},
|
181 |
-
{
|
182 |
-
"data": {
|
183 |
-
"text/plain": [
|
184 |
-
"(8033, 423)"
|
185 |
-
]
|
186 |
-
},
|
187 |
-
"execution_count": 22,
|
188 |
-
"metadata": {},
|
189 |
-
"output_type": "execute_result"
|
190 |
-
}
|
191 |
-
],
|
192 |
"source": [
|
193 |
-
"ds = load_dataset(\"glacierscopessegmentation/
|
|
|
194 |
"\n",
|
195 |
-
"ds = ds
|
196 |
"train_ds = ds[\"train\"]\n",
|
197 |
"test_ds = ds[\"test\"]\n",
|
198 |
"\n",
|
@@ -211,7 +163,33 @@
|
|
211 |
},
|
212 |
{
|
213 |
"cell_type": "code",
|
214 |
-
"execution_count":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
"metadata": {
|
216 |
"colab": {
|
217 |
"base_uri": "https://localhost:8080/",
|
@@ -233,20 +211,7 @@
|
|
233 |
"id": "PAvIJWo1vDb3",
|
234 |
"outputId": "06c909f3-8500-49f6-bca7-b475b1d86885"
|
235 |
},
|
236 |
-
"outputs": [
|
237 |
-
{
|
238 |
-
"name": "stderr",
|
239 |
-
"output_type": "stream",
|
240 |
-
"text": [
|
241 |
-
"c:\\Program Files\\Python310\\lib\\site-packages\\transformers\\models\\segformer\\image_processing_segformer.py:99: FutureWarning: The `reduce_labels` parameter is deprecated and will be removed in a future version. Please use `do_reduce_labels` instead.\n",
|
242 |
-
" warnings.warn(\n",
|
243 |
-
"C:\\Users\\aashr\\AppData\\Roaming\\Python\\Python310\\site-packages\\torch\\storage.py:315: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.\n",
|
244 |
-
" warnings.warn(message, UserWarning)\n",
|
245 |
-
"Some weights of SegformerForSemanticSegmentation were not initialized from the model checkpoint at nvidia/MiT-b0 and are newly initialized: ['decode_head.linear_c.3.proj.weight', 'decode_head.linear_fuse.weight', 'decode_head.classifier.weight', 'decode_head.batch_norm.bias', 'decode_head.linear_c.1.proj.bias', 'decode_head.linear_c.0.proj.bias', 'decode_head.linear_c.1.proj.weight', 'decode_head.linear_c.0.proj.weight', 'decode_head.batch_norm.running_mean', 'decode_head.linear_c.3.proj.bias', 'decode_head.linear_c.2.proj.weight', 'decode_head.batch_norm.num_batches_tracked', 'decode_head.batch_norm.running_var', 'decode_head.classifier.bias', 'decode_head.linear_c.2.proj.bias', 'decode_head.batch_norm.weight']\n",
|
246 |
-
"You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
|
247 |
-
]
|
248 |
-
}
|
249 |
-
],
|
250 |
"source": [
|
251 |
"# Define the checkpoint from which to load the pre-trained model preprocessor\n",
|
252 |
"checkpoint = \"nvidia/MiT-b0\" # We need to use this processor for resizing the images from the dataset to the size expected by the model; the main problem with this is the output scaling for training and testing, so using the right prepreocessor is important\n",
|
@@ -267,13 +232,15 @@
|
|
267 |
"test_image_processor = SegformerImageProcessor.from_pretrained(checkpoint)\n",
|
268 |
"\n",
|
269 |
"# Create a Segformer model for semantic segmentation using the test configuration and move it to the GPU\n",
|
270 |
-
"
|
271 |
-
"\n"
|
|
|
|
|
272 |
]
|
273 |
},
|
274 |
{
|
275 |
"cell_type": "code",
|
276 |
-
"execution_count":
|
277 |
"metadata": {},
|
278 |
"outputs": [],
|
279 |
"source": [
|
@@ -291,7 +258,7 @@
|
|
291 |
},
|
292 |
{
|
293 |
"cell_type": "code",
|
294 |
-
"execution_count":
|
295 |
"metadata": {
|
296 |
"id": "L-Eojv9VvDb3"
|
297 |
},
|
@@ -337,15 +304,21 @@
|
|
337 |
" # This is input that has gone through the model's forward pass\n",
|
338 |
" logits, labels = eval_pred\n",
|
339 |
" logits_tensor = torch.from_numpy(logits)\n",
|
|
|
|
|
|
|
340 |
" # this can lead to very high ram usage for the upscaling\n",
|
341 |
" logits_tensor = nn.functional.interpolate(\n",
|
342 |
" logits_tensor,\n",
|
343 |
-
" size=labels.shape[-2:],\n",
|
344 |
" mode=\"bilinear\",\n",
|
345 |
" align_corners=False,\n",
|
346 |
" )\n",
|
|
|
|
|
|
|
|
|
347 |
" # Take the argmax of the logits tensor along dimension 1 to get the predicted labels\n",
|
348 |
-
" logits_tensor = logits_tensor.argmax(dim=1)\n",
|
349 |
" # Detach the predicted labels from the computation graph and move them to the CPU \n",
|
350 |
" # (although they are already on the CPU) to save memory and to use numpy features like the metrics module\n",
|
351 |
" pred_labels = logits_tensor.detach().cpu().numpy()\n",
|
@@ -374,15 +347,15 @@
|
|
374 |
"training_args = TrainingArguments(\n",
|
375 |
" output_dir=\"glacformer\", # The output directory for the model predictions and checkpoints\n",
|
376 |
" learning_rate=6e-5, # The initial learning rate for Adam\n",
|
377 |
-
" num_train_epochs=
|
378 |
" auto_find_batch_size=True, # Whether to automatically find an appropriate batch size\n",
|
379 |
" save_total_limit=3, # Limit the total amount of checkpoints and delete the older checkpoints\n",
|
380 |
-
" eval_accumulation_steps=
|
381 |
" evaluation_strategy=\"epoch\", # The evaluation strategy to adopt during training\n",
|
382 |
" save_strategy=\"epoch\", # The checkpoint save strategy to adopt during training\n",
|
383 |
" save_steps=1, # Number of updates steps before two checkpoint saves\n",
|
384 |
" eval_steps=1, # Number of update steps before two evaluations\n",
|
385 |
-
" logging_steps=30, # Number of update steps before logging learning rate and other metrics\n",
|
386 |
" remove_unused_columns=False, # Whether to remove columns not used by the model when using a dataset\n",
|
387 |
" fp16=True, # Whether to use 16-bit float precision instead of 32-bit for saving memory\n",
|
388 |
" tf32=True, # Whether to use tf32 precision instead of 32-bit for saving memory\n",
|
@@ -400,6 +373,13 @@
|
|
400 |
")"
|
401 |
]
|
402 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
403 |
{
|
404 |
"cell_type": "code",
|
405 |
"execution_count": null,
|
@@ -419,12 +399,21 @@
|
|
419 |
"trainer.model.save_pretrained(\"glacformer\")\n",
|
420 |
"\n",
|
421 |
"# Create a repository object for the specified repository on Hugging Face's hub, cloning from the specified source\n",
|
422 |
-
"repo = huggingface_hub.Repository(\"
|
|
|
|
|
423 |
"\n",
|
424 |
"repo.git_pull()\n",
|
425 |
"repo.push_to_hub()"
|
426 |
]
|
427 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
428 |
{
|
429 |
"cell_type": "code",
|
430 |
"execution_count": null,
|
@@ -486,6 +475,287 @@
|
|
486 |
"\n",
|
487 |
"glacformer.display(display)"
|
488 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
489 |
}
|
490 |
],
|
491 |
"metadata": {
|
@@ -508,7 +778,7 @@
|
|
508 |
"name": "python",
|
509 |
"nbconvert_exporter": "python",
|
510 |
"pygments_lexer": "ipython3",
|
511 |
-
"version": "3.
|
512 |
},
|
513 |
"widgets": {
|
514 |
"application/vnd.jupyter.widget-state+json": {
|
|
|
2 |
"cells": [
|
3 |
{
|
4 |
"cell_type": "code",
|
5 |
+
"execution_count": null,
|
6 |
"metadata": {
|
7 |
"colab": {
|
8 |
"base_uri": "https://localhost:8080/"
|
|
|
10 |
"id": "c0C76YvrvDbu",
|
11 |
"outputId": "526c8200-e257-45d7-89ec-6c4d6f30d5d0"
|
12 |
},
|
13 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"source": [
|
15 |
"import torch\n",
|
16 |
"import matplotlib.pyplot as plt\n",
|
|
|
51 |
},
|
52 |
{
|
53 |
"cell_type": "code",
|
54 |
+
"execution_count": null,
|
55 |
"metadata": {
|
56 |
"colab": {
|
57 |
"base_uri": "https://localhost:8080/",
|
|
|
139 |
"id": "kOiKU_-vvDb1",
|
140 |
"outputId": "531092ef-a3b9-4156-9d9c-a1835feece0a"
|
141 |
},
|
142 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
"source": [
|
144 |
+
"ds = load_dataset(\"glacierscopessegmentation/scopes\",keep_in_memory=True,)\n",
|
145 |
+
"ds = datasets.concatenate_datasets((ds[\"test\"], ds[\"train\"]))\n",
|
146 |
"\n",
|
147 |
+
"ds = ds.train_test_split(.05)\n",
|
148 |
"train_ds = ds[\"train\"]\n",
|
149 |
"test_ds = ds[\"test\"]\n",
|
150 |
"\n",
|
|
|
163 |
},
|
164 |
{
|
165 |
"cell_type": "code",
|
166 |
+
"execution_count": null,
|
167 |
+
"metadata": {},
|
168 |
+
"outputs": [],
|
169 |
+
"source": [
|
170 |
+
"ds = load_dataset(\"glacierscopessegmentation/scopes\",keep_in_memory=True,)\n",
|
171 |
+
"# ds = datasets.concatenate_datasets((ds[\"test\"], ds[\"train\"]))\n",
|
172 |
+
"\n",
|
173 |
+
"# ds = ds.train_test_split(.05)\n",
|
174 |
+
"# train_ds = ds[\"train\"]\n",
|
175 |
+
"# test_ds = ds[\"test\"]\n",
|
176 |
+
"\n",
|
177 |
+
"id2label = {\n",
|
178 |
+
" \"0\": \"sky\", # This is given by the rgb value of 00 00 00 for the mask\n",
|
179 |
+
" \"1\": \"surface-to-bed\", # This is given by the rgb value of 01 01 01 for the mask\n",
|
180 |
+
" \"2\": \"bed-to-bottom\", # This is given by the rgb value of 02 02 02 for the mask\n",
|
181 |
+
"}\n",
|
182 |
+
"\n",
|
183 |
+
"id2label = {int(k): v for k, v in id2label.items()}\n",
|
184 |
+
"label2id = {v: k for k, v in id2label.items()}\n",
|
185 |
+
"num_labels = len(id2label)\n",
|
186 |
+
"\n",
|
187 |
+
"len(train_ds), len(test_ds)\n"
|
188 |
+
]
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"cell_type": "code",
|
192 |
+
"execution_count": null,
|
193 |
"metadata": {
|
194 |
"colab": {
|
195 |
"base_uri": "https://localhost:8080/",
|
|
|
211 |
"id": "PAvIJWo1vDb3",
|
212 |
"outputId": "06c909f3-8500-49f6-bca7-b475b1d86885"
|
213 |
},
|
214 |
+
"outputs": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
"source": [
|
216 |
"# Define the checkpoint from which to load the pre-trained model preprocessor\n",
|
217 |
"checkpoint = \"nvidia/MiT-b0\" # We need to use this processor for resizing the images from the dataset to the size expected by the model; the main problem with this is the output scaling for training and testing, so using the right prepreocessor is important\n",
|
|
|
232 |
"test_image_processor = SegformerImageProcessor.from_pretrained(checkpoint)\n",
|
233 |
"\n",
|
234 |
"# Create a Segformer model for semantic segmentation using the test configuration and move it to the GPU\n",
|
235 |
+
"\n",
|
236 |
+
"# The line below initializes a blank model, while the new line initializes the model from the huggingface hub\n",
|
237 |
+
"# test_model = SegformerForSemanticSegmentation(test_config).to(\"cuda:0\")\n",
|
238 |
+
"test_model = SegformerForSemanticSegmentation.from_pretrained(hf_model_name,id2label = id2label, label2id = label2id).to(\"cuda:0\")\n"
|
239 |
]
|
240 |
},
|
241 |
{
|
242 |
"cell_type": "code",
|
243 |
+
"execution_count": null,
|
244 |
"metadata": {},
|
245 |
"outputs": [],
|
246 |
"source": [
|
|
|
258 |
},
|
259 |
{
|
260 |
"cell_type": "code",
|
261 |
+
"execution_count": null,
|
262 |
"metadata": {
|
263 |
"id": "L-Eojv9VvDb3"
|
264 |
},
|
|
|
304 |
" # This is input that has gone through the model's forward pass\n",
|
305 |
" logits, labels = eval_pred\n",
|
306 |
" logits_tensor = torch.from_numpy(logits)\n",
|
307 |
+
" \n",
|
308 |
+
" logits_tensor = logits_tensor.argmax(dim=1)\n",
|
309 |
+
" logits_tensor = logits_tensor.unsqueeze(1).to(float)\n",
|
310 |
" # this can lead to very high ram usage for the upscaling\n",
|
311 |
" logits_tensor = nn.functional.interpolate(\n",
|
312 |
" logits_tensor,\n",
|
313 |
+
" size = labels.shape[-2:],\n",
|
314 |
" mode=\"bilinear\",\n",
|
315 |
" align_corners=False,\n",
|
316 |
" )\n",
|
317 |
+
"\n",
|
318 |
+
" # logits_tensor = logits_tensor.argmax(dim=1)\n",
|
319 |
+
" logits_tensor = torch.squeeze(logits_tensor,dim = 1)\n",
|
320 |
+
"\n",
|
321 |
" # Take the argmax of the logits tensor along dimension 1 to get the predicted labels\n",
|
|
|
322 |
" # Detach the predicted labels from the computation graph and move them to the CPU \n",
|
323 |
" # (although they are already on the CPU) to save memory and to use numpy features like the metrics module\n",
|
324 |
" pred_labels = logits_tensor.detach().cpu().numpy()\n",
|
|
|
347 |
"training_args = TrainingArguments(\n",
|
348 |
" output_dir=\"glacformer\", # The output directory for the model predictions and checkpoints\n",
|
349 |
" learning_rate=6e-5, # The initial learning rate for Adam\n",
|
350 |
+
" num_train_epochs=6, # Total number of training epochs to perform\n",
|
351 |
" auto_find_batch_size=True, # Whether to automatically find an appropriate batch size\n",
|
352 |
" save_total_limit=3, # Limit the total amount of checkpoints and delete the older checkpoints\n",
|
353 |
+
" # eval_accumulation_steps=1, # Number of steps to accumulate gradients before performing a backward/update pass\n",
|
354 |
" evaluation_strategy=\"epoch\", # The evaluation strategy to adopt during training\n",
|
355 |
" save_strategy=\"epoch\", # The checkpoint save strategy to adopt during training\n",
|
356 |
" save_steps=1, # Number of updates steps before two checkpoint saves\n",
|
357 |
" eval_steps=1, # Number of update steps before two evaluations\n",
|
358 |
+
" # logging_steps=30, # Number of update steps before logging learning rate and other metrics\n",
|
359 |
" remove_unused_columns=False, # Whether to remove columns not used by the model when using a dataset\n",
|
360 |
" fp16=True, # Whether to use 16-bit float precision instead of 32-bit for saving memory\n",
|
361 |
" tf32=True, # Whether to use tf32 precision instead of 32-bit for saving memory\n",
|
|
|
373 |
")"
|
374 |
]
|
375 |
},
|
376 |
+
{
|
377 |
+
"cell_type": "code",
|
378 |
+
"execution_count": null,
|
379 |
+
"metadata": {},
|
380 |
+
"outputs": [],
|
381 |
+
"source": []
|
382 |
+
},
|
383 |
{
|
384 |
"cell_type": "code",
|
385 |
"execution_count": null,
|
|
|
399 |
"trainer.model.save_pretrained(\"glacformer\")\n",
|
400 |
"\n",
|
401 |
"# Create a repository object for the specified repository on Hugging Face's hub, cloning from the specified source\n",
|
402 |
+
"repo = huggingface_hub.Repository(\"glacformer1\", clone_from=hf_model_name)\n",
|
403 |
+
"\n",
|
404 |
+
"! cp -r glacformer/* glacformer1/\n",
|
405 |
"\n",
|
406 |
"repo.git_pull()\n",
|
407 |
"repo.push_to_hub()"
|
408 |
]
|
409 |
},
|
410 |
+
{
|
411 |
+
"cell_type": "code",
|
412 |
+
"execution_count": null,
|
413 |
+
"metadata": {},
|
414 |
+
"outputs": [],
|
415 |
+
"source": []
|
416 |
+
},
|
417 |
{
|
418 |
"cell_type": "code",
|
419 |
"execution_count": null,
|
|
|
475 |
"\n",
|
476 |
"glacformer.display(display)"
|
477 |
]
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"cell_type": "code",
|
481 |
+
"execution_count": 13,
|
482 |
+
"metadata": {},
|
483 |
+
"outputs": [
|
484 |
+
{
|
485 |
+
"data": {
|
486 |
+
"application/vnd.jupyter.widget-view+json": {
|
487 |
+
"model_id": "032abac7315f4925b32b07a1dd8e8db3",
|
488 |
+
"version_major": 2,
|
489 |
+
"version_minor": 0
|
490 |
+
},
|
491 |
+
"text/plain": [
|
492 |
+
"Map: 0%| | 0/1848 [00:00<?, ? examples/s]"
|
493 |
+
]
|
494 |
+
},
|
495 |
+
"metadata": {},
|
496 |
+
"output_type": "display_data"
|
497 |
+
},
|
498 |
+
{
|
499 |
+
"data": {
|
500 |
+
"application/vnd.jupyter.widget-view+json": {
|
501 |
+
"model_id": "34a7142f36734fff959971c8c335b1c0",
|
502 |
+
"version_major": 2,
|
503 |
+
"version_minor": 0
|
504 |
+
},
|
505 |
+
"text/plain": [
|
506 |
+
"Pushing dataset shards to the dataset hub: 0%| | 0/1 [00:00<?, ?it/s]"
|
507 |
+
]
|
508 |
+
},
|
509 |
+
"metadata": {},
|
510 |
+
"output_type": "display_data"
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"data": {
|
514 |
+
"application/vnd.jupyter.widget-view+json": {
|
515 |
+
"model_id": "8be902f9846b426c82d9c2ea0bccf561",
|
516 |
+
"version_major": 2,
|
517 |
+
"version_minor": 0
|
518 |
+
},
|
519 |
+
"text/plain": [
|
520 |
+
"Creating parquet from Arrow format: 0%| | 0/19 [00:00<?, ?ba/s]"
|
521 |
+
]
|
522 |
+
},
|
523 |
+
"metadata": {},
|
524 |
+
"output_type": "display_data"
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"data": {
|
528 |
+
"application/vnd.jupyter.widget-view+json": {
|
529 |
+
"model_id": "607b7ae0e6d345cfbec7ebf10c6e38ac",
|
530 |
+
"version_major": 2,
|
531 |
+
"version_minor": 0
|
532 |
+
},
|
533 |
+
"text/plain": [
|
534 |
+
"Deleting unused files from dataset repository: 0%| | 0/6 [00:00<?, ?it/s]"
|
535 |
+
]
|
536 |
+
},
|
537 |
+
"metadata": {},
|
538 |
+
"output_type": "display_data"
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"data": {
|
542 |
+
"application/vnd.jupyter.widget-view+json": {
|
543 |
+
"model_id": "e5d424e575d54d5abfb984ef40d16fb7",
|
544 |
+
"version_major": 2,
|
545 |
+
"version_minor": 0
|
546 |
+
},
|
547 |
+
"text/plain": [
|
548 |
+
"Map: 0%| | 0/5851 [00:00<?, ? examples/s]"
|
549 |
+
]
|
550 |
+
},
|
551 |
+
"metadata": {},
|
552 |
+
"output_type": "display_data"
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"data": {
|
556 |
+
"application/vnd.jupyter.widget-view+json": {
|
557 |
+
"model_id": "09796dba22ff47d5ba3204dbe0c79ae1",
|
558 |
+
"version_major": 2,
|
559 |
+
"version_minor": 0
|
560 |
+
},
|
561 |
+
"text/plain": [
|
562 |
+
"Pushing dataset shards to the dataset hub: 0%| | 0/6 [00:00<?, ?it/s]"
|
563 |
+
]
|
564 |
+
},
|
565 |
+
"metadata": {},
|
566 |
+
"output_type": "display_data"
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"data": {
|
570 |
+
"application/vnd.jupyter.widget-view+json": {
|
571 |
+
"model_id": "c98ca8c9d2264ac6bf8cc2a48e0ed268",
|
572 |
+
"version_major": 2,
|
573 |
+
"version_minor": 0
|
574 |
+
},
|
575 |
+
"text/plain": [
|
576 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
577 |
+
]
|
578 |
+
},
|
579 |
+
"metadata": {},
|
580 |
+
"output_type": "display_data"
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"data": {
|
584 |
+
"application/vnd.jupyter.widget-view+json": {
|
585 |
+
"model_id": "520f907923fe4f8e9d52e274eca484c6",
|
586 |
+
"version_major": 2,
|
587 |
+
"version_minor": 0
|
588 |
+
},
|
589 |
+
"text/plain": [
|
590 |
+
"Map: 0%| | 0/5850 [00:00<?, ? examples/s]"
|
591 |
+
]
|
592 |
+
},
|
593 |
+
"metadata": {},
|
594 |
+
"output_type": "display_data"
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"data": {
|
598 |
+
"application/vnd.jupyter.widget-view+json": {
|
599 |
+
"model_id": "304c1699e4e547e49b99b98efb0c92de",
|
600 |
+
"version_major": 2,
|
601 |
+
"version_minor": 0
|
602 |
+
},
|
603 |
+
"text/plain": [
|
604 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
605 |
+
]
|
606 |
+
},
|
607 |
+
"metadata": {},
|
608 |
+
"output_type": "display_data"
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"data": {
|
612 |
+
"application/vnd.jupyter.widget-view+json": {
|
613 |
+
"model_id": "c6586231c59049018016158fb6794f61",
|
614 |
+
"version_major": 2,
|
615 |
+
"version_minor": 0
|
616 |
+
},
|
617 |
+
"text/plain": [
|
618 |
+
"Map: 0%| | 0/5850 [00:00<?, ? examples/s]"
|
619 |
+
]
|
620 |
+
},
|
621 |
+
"metadata": {},
|
622 |
+
"output_type": "display_data"
|
623 |
+
},
|
624 |
+
{
|
625 |
+
"data": {
|
626 |
+
"application/vnd.jupyter.widget-view+json": {
|
627 |
+
"model_id": "f07e6acfc0d74df9a33aafb88afa8821",
|
628 |
+
"version_major": 2,
|
629 |
+
"version_minor": 0
|
630 |
+
},
|
631 |
+
"text/plain": [
|
632 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
633 |
+
]
|
634 |
+
},
|
635 |
+
"metadata": {},
|
636 |
+
"output_type": "display_data"
|
637 |
+
},
|
638 |
+
{
|
639 |
+
"data": {
|
640 |
+
"application/vnd.jupyter.widget-view+json": {
|
641 |
+
"model_id": "12fdc097fbf44edd95eccb5c6c953f3a",
|
642 |
+
"version_major": 2,
|
643 |
+
"version_minor": 0
|
644 |
+
},
|
645 |
+
"text/plain": [
|
646 |
+
"Map: 0%| | 0/5850 [00:00<?, ? examples/s]"
|
647 |
+
]
|
648 |
+
},
|
649 |
+
"metadata": {},
|
650 |
+
"output_type": "display_data"
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"data": {
|
654 |
+
"application/vnd.jupyter.widget-view+json": {
|
655 |
+
"model_id": "9a20d65772b245f5bff202c4f6ed0141",
|
656 |
+
"version_major": 2,
|
657 |
+
"version_minor": 0
|
658 |
+
},
|
659 |
+
"text/plain": [
|
660 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
661 |
+
]
|
662 |
+
},
|
663 |
+
"metadata": {},
|
664 |
+
"output_type": "display_data"
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"data": {
|
668 |
+
"application/vnd.jupyter.widget-view+json": {
|
669 |
+
"model_id": "2911bb4684894749b9188e1cd9e5d977",
|
670 |
+
"version_major": 2,
|
671 |
+
"version_minor": 0
|
672 |
+
},
|
673 |
+
"text/plain": [
|
674 |
+
"Map: 0%| | 0/5850 [00:00<?, ? examples/s]"
|
675 |
+
]
|
676 |
+
},
|
677 |
+
"metadata": {},
|
678 |
+
"output_type": "display_data"
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"data": {
|
682 |
+
"application/vnd.jupyter.widget-view+json": {
|
683 |
+
"model_id": "397fc1c8116f4280a49160432314e4d6",
|
684 |
+
"version_major": 2,
|
685 |
+
"version_minor": 0
|
686 |
+
},
|
687 |
+
"text/plain": [
|
688 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
689 |
+
]
|
690 |
+
},
|
691 |
+
"metadata": {},
|
692 |
+
"output_type": "display_data"
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"data": {
|
696 |
+
"application/vnd.jupyter.widget-view+json": {
|
697 |
+
"model_id": "aa14f6db540e4633a84ef3edfffec6a3",
|
698 |
+
"version_major": 2,
|
699 |
+
"version_minor": 0
|
700 |
+
},
|
701 |
+
"text/plain": [
|
702 |
+
"Map: 0%| | 0/5850 [00:00<?, ? examples/s]"
|
703 |
+
]
|
704 |
+
},
|
705 |
+
"metadata": {},
|
706 |
+
"output_type": "display_data"
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"data": {
|
710 |
+
"application/vnd.jupyter.widget-view+json": {
|
711 |
+
"model_id": "7c675a39c05a4288bce0248991e7a568",
|
712 |
+
"version_major": 2,
|
713 |
+
"version_minor": 0
|
714 |
+
},
|
715 |
+
"text/plain": [
|
716 |
+
"Creating parquet from Arrow format: 0%| | 0/59 [00:00<?, ?ba/s]"
|
717 |
+
]
|
718 |
+
},
|
719 |
+
"metadata": {},
|
720 |
+
"output_type": "display_data"
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"data": {
|
724 |
+
"application/vnd.jupyter.widget-view+json": {
|
725 |
+
"model_id": "ad22a4f84b56495e86319a5715064cb9",
|
726 |
+
"version_major": 2,
|
727 |
+
"version_minor": 0
|
728 |
+
},
|
729 |
+
"text/plain": [
|
730 |
+
"Deleting unused files from dataset repository: 0%| | 0/1 [00:00<?, ?it/s]"
|
731 |
+
]
|
732 |
+
},
|
733 |
+
"metadata": {},
|
734 |
+
"output_type": "display_data"
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"data": {
|
738 |
+
"application/vnd.jupyter.widget-view+json": {
|
739 |
+
"model_id": "ab8fcfdc61534e718e2672baf9b103b4",
|
740 |
+
"version_major": 2,
|
741 |
+
"version_minor": 0
|
742 |
+
},
|
743 |
+
"text/plain": [
|
744 |
+
"Downloading metadata: 0%| | 0.00/664 [00:00<?, ?B/s]"
|
745 |
+
]
|
746 |
+
},
|
747 |
+
"metadata": {},
|
748 |
+
"output_type": "display_data"
|
749 |
+
}
|
750 |
+
],
|
751 |
+
"source": [
|
752 |
+
"from datasets import DatasetDict\n",
|
753 |
+
"\n",
|
754 |
+
"dd = DatasetDict({\"test\":test_ds,\"train\":train_ds})\n",
|
755 |
+
"\n",
|
756 |
+
"dd.push_to_hub(\"glacierscopessegmentation/scopes\")\n",
|
757 |
+
"\n"
|
758 |
+
]
|
759 |
}
|
760 |
],
|
761 |
"metadata": {
|
|
|
778 |
"name": "python",
|
779 |
"nbconvert_exporter": "python",
|
780 |
"pygments_lexer": "ipython3",
|
781 |
+
"version": "3.11.5"
|
782 |
},
|
783 |
"widgets": {
|
784 |
"application/vnd.jupyter.widget-state+json": {
|