File size: 13,605 Bytes
473dfd0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!pip install transformers dataset\n",
        "!pip install -q gradio\n",
        "!pip install sentencepiece\n",
        "!pip install googletrans==3.1.0a0"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Vbo2y6IyU9EE",
        "outputId": "fba9099a-c64b-4f9e-864f-0c59698a7633"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: transformers in /usr/local/lib/python3.8/dist-packages (4.26.0)\n",
            "Requirement already satisfied: dataset in /usr/local/lib/python3.8/dist-packages (1.6.0)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.8/dist-packages (from transformers) (0.12.0)\n",
            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.8/dist-packages (from transformers) (0.13.2)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.8/dist-packages (from transformers) (1.21.6)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.8/dist-packages (from transformers) (4.64.1)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.8/dist-packages (from transformers) (2.25.1)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.8/dist-packages (from transformers) (2022.6.2)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.8/dist-packages (from transformers) (6.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.8/dist-packages (from transformers) (3.9.0)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.8/dist-packages (from transformers) (23.0)\n",
            "Requirement already satisfied: sqlalchemy<2.0.0,>=1.3.2 in /usr/local/lib/python3.8/dist-packages (from dataset) (1.4.46)\n",
            "Requirement already satisfied: alembic>=0.6.2 in /usr/local/lib/python3.8/dist-packages (from dataset) (1.9.2)\n",
            "Requirement already satisfied: banal>=1.0.1 in /usr/local/lib/python3.8/dist-packages (from dataset) (1.0.6)\n",
            "Requirement already satisfied: importlib-metadata in /usr/local/lib/python3.8/dist-packages (from alembic>=0.6.2->dataset) (6.0.0)\n",
            "Requirement already satisfied: Mako in /usr/local/lib/python3.8/dist-packages (from alembic>=0.6.2->dataset) (1.2.4)\n",
            "Requirement already satisfied: importlib-resources in /usr/local/lib/python3.8/dist-packages (from alembic>=0.6.2->dataset) (5.10.2)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.8/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.4.0)\n",
            "Requirement already satisfied: greenlet!=0.4.17 in /usr/local/lib/python3.8/dist-packages (from sqlalchemy<2.0.0,>=1.3.2->dataset) (2.0.2)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (1.24.3)\n",
            "Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (3.0.4)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (2.10)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (2022.12.7)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.8/dist-packages (from importlib-metadata->alembic>=0.6.2->dataset) (3.12.0)\n",
            "Requirement already satisfied: MarkupSafe>=0.9.2 in /usr/local/lib/python3.8/dist-packages (from Mako->alembic>=0.6.2->dataset) (2.0.1)\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.8/dist-packages (0.1.97)\n",
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: googletrans==3.1.0a0 in /usr/local/lib/python3.8/dist-packages (3.1.0a0)\n",
            "Requirement already satisfied: httpx==0.13.3 in /usr/local/lib/python3.8/dist-packages (from googletrans==3.1.0a0) (0.13.3)\n",
            "Requirement already satisfied: idna==2.* in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (2.10)\n",
            "Requirement already satisfied: certifi in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (2022.12.7)\n",
            "Requirement already satisfied: rfc3986<2,>=1.3 in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (1.5.0)\n",
            "Requirement already satisfied: chardet==3.* in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (3.0.4)\n",
            "Requirement already satisfied: httpcore==0.9.* in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (0.9.1)\n",
            "Requirement already satisfied: sniffio in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (1.3.0)\n",
            "Requirement already satisfied: hstspreload in /usr/local/lib/python3.8/dist-packages (from httpx==0.13.3->googletrans==3.1.0a0) (2023.1.1)\n",
            "Requirement already satisfied: h2==3.* in /usr/local/lib/python3.8/dist-packages (from httpcore==0.9.*->httpx==0.13.3->googletrans==3.1.0a0) (3.2.0)\n",
            "Requirement already satisfied: h11<0.10,>=0.8 in /usr/local/lib/python3.8/dist-packages (from httpcore==0.9.*->httpx==0.13.3->googletrans==3.1.0a0) (0.9.0)\n",
            "Requirement already satisfied: hpack<4,>=3.0 in /usr/local/lib/python3.8/dist-packages (from h2==3.*->httpcore==0.9.*->httpx==0.13.3->googletrans==3.1.0a0) (3.0.0)\n",
            "Requirement already satisfied: hyperframe<6,>=5.2.0 in /usr/local/lib/python3.8/dist-packages (from h2==3.*->httpcore==0.9.*->httpx==0.13.3->googletrans==3.1.0a0) (5.2.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 64,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 723
        },
        "id": "5DNOX2BIU5mO",
        "outputId": "9311e1ba-5685-4f74-e40a-0f1cd39484d0"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Using cache found in /root/.cache/torch/hub/pytorch_vision_v0.6.0\n",
            "/usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.\n",
            "  warnings.warn(\n",
            "/usr/local/lib/python3.8/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=ResNet18_Weights.IMAGENET1K_V1`. You can also use `weights=ResNet18_Weights.DEFAULT` to get the most up-to-date weights.\n",
            "  warnings.warn(msg)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n",
            "Note: opening Chrome Inspector may crash demo inside Colab notebooks.\n",
            "\n",
            "To create a public link, set `share=True` in `launch()`.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "(async (port, path, width, height, cache, element) => {\n",
              "                        if (!google.colab.kernel.accessAllowed && !cache) {\n",
              "                            return;\n",
              "                        }\n",
              "                        element.appendChild(document.createTextNode(''));\n",
              "                        const url = await google.colab.kernel.proxyPort(port, {cache});\n",
              "\n",
              "                        const external_link = document.createElement('div');\n",
              "                        external_link.innerHTML = `\n",
              "                            <div style=\"font-family: monospace; margin-bottom: 0.5rem\">\n",
              "                                Running on <a href=${new URL(path, url).toString()} target=\"_blank\">\n",
              "                                    https://localhost:${port}${path}\n",
              "                                </a>\n",
              "                            </div>\n",
              "                        `;\n",
              "                        element.appendChild(external_link);\n",
              "\n",
              "                        const iframe = document.createElement('iframe');\n",
              "                        iframe.src = new URL(path, url).toString();\n",
              "                        iframe.height = height;\n",
              "                        iframe.allow = \"autoplay; camera; microphone; clipboard-read; clipboard-write;\"\n",
              "                        iframe.width = width;\n",
              "                        iframe.style.border = 0;\n",
              "                        element.appendChild(iframe);\n",
              "                    })(7882, \"/\", \"100%\", 500, false, window.element)"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": []
          },
          "metadata": {},
          "execution_count": 64
        }
      ],
      "source": [
        "import gradio as gr\n",
        "import requests\n",
        "from PIL import Image\n",
        "from torchvision import transforms\n",
        "from transformers import pipeline\n",
        "import torch\n",
        "import sentencepiece\n",
        "import re\n",
        "import googletrans \n",
        "from googletrans import Translator\n",
        "\n",
        "model = torch.hub.load('pytorch/vision:v0.6.0', 'resnet18', pretrained=True).eval()\n",
        "\n",
        "from transformers import SegformerFeatureExtractor, SegformerForImageClassification,  T5Tokenizer, T5Model\n",
        "from PIL import Image\n",
        "import requests\n",
        "\n",
        "\n",
        "def loadImageToText(image, argument):\n",
        "  # url = \"https://media.istockphoto.com/id/470604022/es/foto/%C3%A1rbol-de-manzano.jpg?s=1024x1024&w=is&k=20&c=R7b6jPeTGsDw75Sqn3VwpNRckqlAkJNPLelb48pCk2U=\"\n",
        "  # image = Image.open(requests.get(url, stream=True).raw)\n",
        "  feature_extractor = SegformerFeatureExtractor.from_pretrained(\"nvidia/mit-b2\")\n",
        "  model = SegformerForImageClassification.from_pretrained(\"nvidia/mit-b2\")\n",
        "  translator = Translator()\n",
        "\n",
        "  inputs = feature_extractor(images=image, return_tensors=\"pt\")\n",
        "  outputs = model(**inputs)\n",
        "  logits = outputs.logits\n",
        "  # model predicts one of the 1000 ImageNet classes\n",
        "  predicted_class_idx = logits.argmax(-1).item()\n",
        "  part_args = f\"<\"+re.sub(\"[^(\\w|<|>)]+(?=\\w)\", \"><\", argument) + \">\"\n",
        "  story_gen = pipeline(\"text-generation\", \"pranavpsv/gpt2-genre-story-generator\")\n",
        "  story_text = story_gen(part_args + model.config.id2label[predicted_class_idx])\n",
        "\n",
        "  generate_text_stroy = story_text[0][\"generated_text\"]\n",
        "  ln_text_story = generate_text_stroy[len(part_args):len(generate_text_stroy)]\n",
        "\n",
        "  translated_ita = translator.translate(ln_text_story, src='en', dest='es')\n",
        "\n",
        "  return translated_ita.text\n",
        "\n",
        "\n",
        "\n",
        "#print(loadImageToText(\"animal,super\")) # borra el argumento 'image' y sus variables internas si quieres probarlo desde aquí.\n",
        "\n",
        "gr.Interface(fn=loadImageToText,\n",
        "             inputs=[gr.Image(), gr.Text(label=\"Argumentos base\", placeholder=\"Verano, película,playa, superhéroe, animal\")],\n",
        "             outputs=\"text\").launch()\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "zMmh7-ixXNIH"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}